Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1603 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0509. Min Range: -6.0509
Max Act: 6.0509. Min Act: -0.1700
Data Index: 1189426 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.8009. Min Act: -0.1700
Data Index: 1318873 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7697. Min Act: -0.1700
Data Index: 520829 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7697. Min Act: -0.1700
Data Index: 7505687 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7384. Min Act: -0.1700
Data Index: 5606816 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7384. Min Act: -0.1700
Data Index: 6885110 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.6759. Min Act: -0.1700
Data Index: 7040957 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.6447. Min Act: -0.1700
Data Index: 4509713 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.5822. Min Act: -0.1700
Data Index: 8393390 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.5822. Min Act: -0.1700
Data Index: 1683107 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.6134. Min Act: -0.1700
Data Index: 4921553 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.5822. Min Act: -0.1700
Data Index: 6885109 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.5822. Min Act: -0.1700
Data Index: 4479691 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.5822. Min Act: -0.1700
Data Index: 425861 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.5197. Min Act: -0.1700
Data Index: 6262610 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.5197. Min Act: -0.1700
Data Index: 7915062 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.5509. Min Act: -0.1700
Data Index: 1562063 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.5197. Min Act: -0.1700
Data Index: 4636013 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.5197. Min Act: -0.1700
Data Index: 6987818 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.4884. Min Act: -0.1700
Data Index: 4639978 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19