Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 684 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4054. Min Range: -6.4054
Max Act: 6.4054. Min Act: -0.1700
Data Index: 7175870 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4054. Min Range: -6.4054
Max Act: 6.4054. Min Act: -0.1700
Data Index: 753101 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4054. Min Range: -6.4054
Max Act: 6.2492. Min Act: -0.1700
Data Index: 8774423 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4054. Min Range: -6.4054
Max Act: 6.1867. Min Act: -0.1700
Data Index: 4637470 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4054. Min Range: -6.4054
Max Act: 6.1554. Min Act: -0.1700
Data Index: 2430967 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4054. Min Range: -6.4054
Max Act: 6.1242. Min Act: -0.1700
Data Index: 4698799 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4054. Min Range: -6.4054
Max Act: 6.0929. Min Act: -0.1700
Data Index: 3480542 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4054. Min Range: -6.4054
Max Act: 6.0929. Min Act: -0.1700
Data Index: 3581272 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4054. Min Range: -6.4054
Max Act: 6.0929. Min Act: -0.1700
Data Index: 3391775 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4054. Min Range: -6.4054
Max Act: 6.0304. Min Act: -0.1700
Data Index: 5757635 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4054. Min Range: -6.4054
Max Act: 5.9679. Min Act: -0.1700
Data Index: 6099709 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4054. Min Range: -6.4054
Max Act: 5.9992. Min Act: -0.1700
Data Index: 5018383 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4054. Min Range: -6.4054
Max Act: 5.9679. Min Act: -0.1700
Data Index: 8250594 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4054. Min Range: -6.4054
Max Act: 5.9679. Min Act: -0.1700
Data Index: 6216897 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4054. Min Range: -6.4054
Max Act: 5.9367. Min Act: -0.1700
Data Index: 6826835 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4054. Min Range: -6.4054
Max Act: 5.9679. Min Act: -0.1700
Data Index: 1572949 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4054. Min Range: -6.4054
Max Act: 5.9679. Min Act: -0.1700
Data Index: 89251 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4054. Min Range: -6.4054
Max Act: 5.8742. Min Act: -0.1700
Data Index: 5988965 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4054. Min Range: -6.4054
Max Act: 5.9054. Min Act: -0.1700
Data Index: 7125853 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4054. Min Range: -6.4054
Max Act: 5.9054. Min Act: -0.1700
Data Index: 2508294 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19