Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2611 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1981. Min Range: -9.1981
Max Act: 9.1981. Min Act: -0.1700
Data Index: 3147372 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.8856. Min Act: -0.1700
Data Index: 2117549 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.6981. Min Act: -0.1700
Data Index: 1522019 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.6356. Min Act: -0.1700
Data Index: 2481097 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.4481. Min Act: -0.1700
Data Index: 4365428 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.4481. Min Act: -0.1700
Data Index: 5402182 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.4481. Min Act: -0.1700
Data Index: 6049468 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.3856. Min Act: -0.1700
Data Index: 7272617 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.4481. Min Act: -0.1700
Data Index: 2859304 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.3856. Min Act: -0.1700
Data Index: 3833121 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.3231. Min Act: -0.1700
Data Index: 2066724 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.3856. Min Act: -0.1700
Data Index: 5748696 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.2606. Min Act: -0.1700
Data Index: 593380 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.3856. Min Act: -0.1700
Data Index: 8284422 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.2606. Min Act: -0.1700
Data Index: 3397697 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.3231. Min Act: -0.1700
Data Index: 8102140 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.2606. Min Act: -0.1700
Data Index: 467119 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.1981. Min Act: -0.1700
Data Index: 5237669 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.2606. Min Act: -0.1700
Data Index: 2710134 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1981. Min Range: -9.1981
Max Act: 8.2606. Min Act: -0.1700
Data Index: 1702741 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19