Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3095 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.3765. Min Act: -0.1700
Data Index: 1017967 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.3608. Min Act: -0.1700
Data Index: 4597140 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.2824. Min Act: -0.1700
Data Index: 4584215 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.2824. Min Act: -0.1700
Data Index: 1650638 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.2667. Min Act: -0.1700
Data Index: 3844394 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.2352. Min Act: -0.1700
Data Index: 2015007 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.2509. Min Act: -0.1700
Data Index: 4560938 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.2038. Min Act: -0.1700
Data Index: 8594542 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.2038. Min Act: -0.1700
Data Index: 4016722 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.1723. Min Act: -0.1700
Data Index: 3497176 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.1566. Min Act: -0.1700
Data Index: 6421275 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.1566. Min Act: -0.1700
Data Index: 3575459 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.1409. Min Act: -0.1700
Data Index: 5163927 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.1251. Min Act: -0.1700
Data Index: 7122638 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.1409. Min Act: -0.1700
Data Index: 3795016 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.1251. Min Act: -0.1700
Data Index: 8119761 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.1409. Min Act: -0.1700
Data Index: 3533367 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.1409. Min Act: -0.1700
Data Index: 8010215 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.1094. Min Act: -0.1700
Data Index: 6069385 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3765. Min Range: -3.3765
Max Act: 3.1094. Min Act: -0.1700
Data Index: 5034206 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19