Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 217 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.5219. Min Act: -0.1700
Data Index: 2380868 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.4282. Min Act: -0.1700
Data Index: 4755256 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.3969. Min Act: -0.1700
Data Index: 5231799 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.3657. Min Act: -0.1700
Data Index: 4791005 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.3344. Min Act: -0.1700
Data Index: 7208161 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.3032. Min Act: -0.1700
Data Index: 5211741 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.3657. Min Act: -0.1700
Data Index: 4330506 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.3032. Min Act: -0.1700
Data Index: 2444403 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2719. Min Act: -0.1700
Data Index: 4701767 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2719. Min Act: -0.1700
Data Index: 853329 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2719. Min Act: -0.1700
Data Index: 2763735 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2719. Min Act: -0.1699
Data Index: 8325797 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2719. Min Act: -0.1700
Data Index: 5994646 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2719. Min Act: -0.1700
Data Index: 5608971 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2719. Min Act: -0.1700
Data Index: 5911672 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2719. Min Act: -0.1700
Data Index: 3430977 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2094. Min Act: -0.1700
Data Index: 2667696 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2407. Min Act: -0.1700
Data Index: 4747030 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2407. Min Act: -0.1700
Data Index: 400678 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2407. Min Act: -0.1700
Data Index: 3445247 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19