Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4641 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3360. Min Range: -12.3360
Max Act: 12.3360. Min Act: -0.1700
Data Index: 3878117 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3360. Min Range: -12.3360
Max Act: 12.3360. Min Act: -0.1700
Data Index: 7907114 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3360. Min Range: -12.3360
Max Act: 12.3360. Min Act: -0.1700
Data Index: 4716629 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3360. Min Range: -12.3360
Max Act: 12.2110. Min Act: -0.1699
Data Index: 1044579 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3360. Min Range: -12.3360
Max Act: 12.1485. Min Act: -0.1700
Data Index: 1209380 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3360. Min Range: -12.3360
Max Act: 12.1485. Min Act: -0.1695
Data Index: 5185568 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3360. Min Range: -12.3360
Max Act: 12.0235. Min Act: -0.1699
Data Index: 5263218 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3360. Min Range: -12.3360
Max Act: 12.0860. Min Act: -0.1700
Data Index: 4633514 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3360. Min Range: -12.3360
Max Act: 12.0235. Min Act: -0.1700
Data Index: 3290492 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3360. Min Range: -12.3360
Max Act: 12.0235. Min Act: -0.1698
Data Index: 8066680 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3360. Min Range: -12.3360
Max Act: 11.9610. Min Act: -0.1699
Data Index: 2567110 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3360. Min Range: -12.3360
Max Act: 11.9610. Min Act: -0.1667
Data Index: 2489545 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3360. Min Range: -12.3360
Max Act: 11.9610. Min Act: -0.1700
Data Index: 5453645 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3360. Min Range: -12.3360
Max Act: 11.9610. Min Act: -0.1700
Data Index: 7970209 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3360. Min Range: -12.3360
Max Act: 11.8985. Min Act: -0.1697
Data Index: 6998880 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3360. Min Range: -12.3360
Max Act: 11.8985. Min Act: -0.1700
Data Index: 5540550 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3360. Min Range: -12.3360
Max Act: 11.9610. Min Act: -0.1699
Data Index: 6446471 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3360. Min Range: -12.3360
Max Act: 11.8360. Min Act: -0.1699
Data Index: 5684185 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3360. Min Range: -12.3360
Max Act: 11.8985. Min Act: -0.1700
Data Index: 5734111 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3360. Min Range: -12.3360
Max Act: 11.8360. Min Act: -0.1700
Data Index: 1396124 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19