Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.9559. Min Act: -0.1700
Data Index: 4409227 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.9247. Min Act: -0.1700
Data Index: 4740771 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.9247. Min Act: -0.1700
Data Index: 980121 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.9247. Min Act: -0.1700
Data Index: 3223332 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.8309. Min Act: -0.1700
Data Index: 4717369 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7997. Min Act: -0.1700
Data Index: 1261750 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7997. Min Act: -0.1700
Data Index: 4082533 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7997. Min Act: -0.1700
Data Index: 5409793 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7684. Min Act: -0.1700
Data Index: 4081754 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7684. Min Act: -0.1700
Data Index: 4498660 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7372. Min Act: -0.1700
Data Index: 7417500 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7059. Min Act: -0.1700
Data Index: 6686569 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7372. Min Act: -0.1700
Data Index: 1747842 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7372. Min Act: -0.1700
Data Index: 149199 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7372. Min Act: -0.1700
Data Index: 8261996 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7059. Min Act: -0.1700
Data Index: 639578 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.6747. Min Act: -0.1700
Data Index: 1943578 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7059. Min Act: -0.1700
Data Index: 3310739 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7059. Min Act: -0.1700
Data Index: 3983726 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9559. Min Range: -5.9559
Max Act: 5.7059. Min Act: -0.1700
Data Index: 1470177 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19