Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4338 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.2770. Min Act: -0.1700
Data Index: 6426222 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.2770. Min Act: -0.1700
Data Index: 2779491 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.2458. Min Act: -0.1700
Data Index: 8745299 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1520. Min Act: -0.1700
Data Index: 525007 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1520. Min Act: -0.1700
Data Index: 5354380 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1208. Min Act: -0.1700
Data Index: 7572216 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.0895. Min Act: -0.1700
Data Index: 963908 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1208. Min Act: -0.1700
Data Index: 1980349 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.0895. Min Act: -0.1700
Data Index: 6944529 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.0270. Min Act: -0.1700
Data Index: 6463623 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2770. Min Range: -5.2770
Max Act: 4.9958. Min Act: -0.1700
Data Index: 6536918 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2770. Min Range: -5.2770
Max Act: 4.9958. Min Act: -0.1700
Data Index: 8053630 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2770. Min Range: -5.2770
Max Act: 4.9645. Min Act: -0.1700
Data Index: 4928805 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2770. Min Range: -5.2770
Max Act: 4.9958. Min Act: -0.1700
Data Index: 3407708 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2770. Min Range: -5.2770
Max Act: 4.9645. Min Act: -0.1700
Data Index: 4616441 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2770. Min Range: -5.2770
Max Act: 4.9958. Min Act: -0.1700
Data Index: 4355027 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2770. Min Range: -5.2770
Max Act: 4.9645. Min Act: -0.1700
Data Index: 6900717 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2770. Min Range: -5.2770
Max Act: 4.9645. Min Act: -0.1700
Data Index: 3309933 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2770. Min Range: -5.2770
Max Act: 4.9333. Min Act: -0.1700
Data Index: 5006489 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2770. Min Range: -5.2770
Max Act: 4.9333. Min Act: -0.1700
Data Index: 6132955 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19