Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2491 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0824. Min Range: -5.0824
Max Act: 5.0824. Min Act: -0.1700
Data Index: 8006238 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0824. Min Range: -5.0824
Max Act: 5.0824. Min Act: -0.1700
Data Index: 1515841 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0824. Min Range: -5.0824
Max Act: 5.0199. Min Act: -0.1700
Data Index: 7462145 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.9886. Min Act: -0.1700
Data Index: 7367612 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.9574. Min Act: -0.1700
Data Index: 861144 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.8636. Min Act: -0.1700
Data Index: 2691311 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.8324. Min Act: -0.1700
Data Index: 4557862 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.8011. Min Act: -0.1700
Data Index: 3222281 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.7699. Min Act: -0.1700
Data Index: 4581181 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.7386. Min Act: -0.1700
Data Index: 7126376 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.7699. Min Act: -0.1700
Data Index: 8024846 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.7699. Min Act: -0.1700
Data Index: 6813921 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.7386. Min Act: -0.1700
Data Index: 4735926 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.7386. Min Act: -0.1700
Data Index: 6074643 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.7386. Min Act: -0.1700
Data Index: 1972827 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.6761. Min Act: -0.1700
Data Index: 1401676 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.7074. Min Act: -0.1700
Data Index: 5299174 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.7074. Min Act: -0.1700
Data Index: 305759 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.7074. Min Act: -0.1700
Data Index: 281009 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0824. Min Range: -5.0824
Max Act: 4.6449. Min Act: -0.1700
Data Index: 7281815 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19