Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 228 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1980. Min Range: -6.1980
Max Act: 6.1980. Min Act: -0.1700
Data Index: 2366747 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.8230. Min Act: -0.1700
Data Index: 6163802 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.8230. Min Act: -0.1700
Data Index: 5518364 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.7292. Min Act: -0.1700
Data Index: 2156785 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.6667. Min Act: -0.1700
Data Index: 3310657 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.6667. Min Act: -0.1700
Data Index: 636057 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.6355. Min Act: -0.1700
Data Index: 3125538 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.6667. Min Act: -0.1700
Data Index: 1396389 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.6980. Min Act: -0.1700
Data Index: 3080997 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.6355. Min Act: -0.1700
Data Index: 1489285 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.5730. Min Act: -0.1700
Data Index: 1287030 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.5730. Min Act: -0.1700
Data Index: 4527867 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.5730. Min Act: -0.1700
Data Index: 8434731 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.5105. Min Act: -0.1700
Data Index: 6163791 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.5105. Min Act: -0.1700
Data Index: 4965264 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.5105. Min Act: -0.1700
Data Index: 2011243 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.4792. Min Act: -0.1700
Data Index: 4760110 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.4792. Min Act: -0.1700
Data Index: 2753133 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.5105. Min Act: -0.1700
Data Index: 2972866 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1980. Min Range: -6.1980
Max Act: 5.4480. Min Act: -0.1700
Data Index: 1180249 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19