Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4315 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.7904. Min Act: -0.1700
Data Index: 1288673 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.8217. Min Act: -0.1700
Data Index: 2219059 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.3217. Min Act: -0.1700
Data Index: 7676854 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.2904. Min Act: -0.1700
Data Index: 815367 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.2592. Min Act: -0.1700
Data Index: 7899913 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.2279. Min Act: -0.1700
Data Index: 8743879 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.2592. Min Act: -0.1700
Data Index: 7230277 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.1967. Min Act: -0.1700
Data Index: 6250371 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.1967. Min Act: -0.1700
Data Index: 4330015 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.1967. Min Act: -0.1700
Data Index: 8000629 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.1967. Min Act: -0.1700
Data Index: 7504449 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.1654. Min Act: -0.1700
Data Index: 3745876 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.1967. Min Act: -0.1700
Data Index: 7280807 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.1342. Min Act: -0.1700
Data Index: 3732204 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.1342. Min Act: -0.1700
Data Index: 3432278 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.1029. Min Act: -0.1700
Data Index: 1421082 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.0717. Min Act: -0.1700
Data Index: 7696084 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.1342. Min Act: -0.1700
Data Index: 1151606 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.1029. Min Act: -0.1700
Data Index: 1840837 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8217. Min Range: -5.8217
Max Act: 5.1029. Min Act: -0.1700
Data Index: 8591844 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19