Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1704 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.4801. Min Act: -0.1700
Data Index: 2734922 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.5125. Min Act: -0.1700
Data Index: 5163531 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.3824. Min Act: -0.1700
Data Index: 2847631 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.3824. Min Act: -0.1700
Data Index: 4648832 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.3661. Min Act: -0.1700
Data Index: 4584584 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.3661. Min Act: -0.1700
Data Index: 3077980 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.3333. Min Act: -0.1700
Data Index: 3938944 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.3333. Min Act: -0.1700
Data Index: 397440 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.3333. Min Act: -0.1700
Data Index: 891013 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.3169. Min Act: -0.1700
Data Index: 1861415 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.3169. Min Act: -0.1700
Data Index: 5292986 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.3004. Min Act: -0.1700
Data Index: 4336407 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.3169. Min Act: -0.1700
Data Index: 8247485 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.3004. Min Act: -0.1700
Data Index: 5457295 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.2840. Min Act: -0.1700
Data Index: 4940464 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.3004. Min Act: -0.1700
Data Index: 3139247 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.2840. Min Act: -0.1700
Data Index: 7126186 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.2840. Min Act: -0.1700
Data Index: 6286319 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.2840. Min Act: -0.1700
Data Index: 3302733 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5125. Min Range: -2.5125
Max Act: 2.2675. Min Act: -0.1700
Data Index: 1367659 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19