Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6388 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1623. Min Range: -9.1623
Max Act: 9.1623. Min Act: -0.1700
Data Index: 1515260 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.8498. Min Act: -0.1700
Data Index: 5730481 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.6623. Min Act: -0.1700
Data Index: 5915626 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.6623. Min Act: -0.1700
Data Index: 3597466 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.5998. Min Act: -0.1700
Data Index: 7468019 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.5998. Min Act: -0.1700
Data Index: 361484 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.5373. Min Act: -0.1700
Data Index: 5562125 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.5373. Min Act: -0.1700
Data Index: 8202692 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.4748. Min Act: -0.1700
Data Index: 24775 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.4748. Min Act: -0.1700
Data Index: 3451333 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.4123. Min Act: -0.1700
Data Index: 2333139 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.3498. Min Act: -0.1700
Data Index: 7742967 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.3498. Min Act: -0.1700
Data Index: 7596341 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.3498. Min Act: -0.1700
Data Index: 1823524 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.3498. Min Act: -0.1700
Data Index: 1292218 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.3498. Min Act: -0.1700
Data Index: 1398661 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.3498. Min Act: -0.1700
Data Index: 3733534 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.3498. Min Act: -0.1700
Data Index: 2073030 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.2873. Min Act: -0.1700
Data Index: 3139267 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1623. Min Range: -9.1623
Max Act: 8.2873. Min Act: -0.1700
Data Index: 7174153 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19