Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1288 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3906. Min Range: -9.3906
Max Act: 9.3906. Min Act: -0.1700
Data Index: 7373923 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.9531. Min Act: -0.1700
Data Index: 8335523 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.9531. Min Act: -0.1700
Data Index: 5864935 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.8906. Min Act: -0.1700
Data Index: 8289216 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.8281. Min Act: -0.1700
Data Index: 7548852 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.8281. Min Act: -0.1700
Data Index: 2486973 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.8281. Min Act: -0.1700
Data Index: 4345157 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.6406. Min Act: -0.1700
Data Index: 5368265 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.6406. Min Act: -0.1700
Data Index: 6603651 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.4531. Min Act: -0.1700
Data Index: 6706691 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.3281. Min Act: -0.1700
Data Index: 4792503 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.2656. Min Act: -0.1700
Data Index: 5410988 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.3281. Min Act: -0.1700
Data Index: 5447753 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.3281. Min Act: -0.1700
Data Index: 8728181 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.2031. Min Act: -0.1700
Data Index: 5449558 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.3281. Min Act: -0.1700
Data Index: 8048895 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.3281. Min Act: -0.1700
Data Index: 2201161 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.2656. Min Act: -0.1700
Data Index: 3785576 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.1406. Min Act: -0.1700
Data Index: 7124499 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3906. Min Range: -9.3906
Max Act: 8.1406. Min Act: -0.1700
Data Index: 5488993 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19