Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2931 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1054. Min Range: -6.1054
Max Act: 6.1054. Min Act: -0.1700
Data Index: 5230001 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.6679. Min Act: -0.1700
Data Index: 4668776 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.6367. Min Act: -0.1700
Data Index: 587330 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.6679. Min Act: -0.1700
Data Index: 4064739 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.6054. Min Act: -0.1700
Data Index: 737038 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.5742. Min Act: -0.1700
Data Index: 1015746 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.6367. Min Act: -0.1700
Data Index: 8360556 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.6054. Min Act: -0.1700
Data Index: 7675974 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.5742. Min Act: -0.1700
Data Index: 5177100 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.5117. Min Act: -0.1700
Data Index: 2884064 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.5117. Min Act: -0.1700
Data Index: 6940423 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.5117. Min Act: -0.1700
Data Index: 1623286 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.5117. Min Act: -0.1700
Data Index: 6557878 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.4492. Min Act: -0.1700
Data Index: 1946003 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.4492. Min Act: -0.1700
Data Index: 5192324 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.4492. Min Act: -0.1700
Data Index: 958595 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.4179. Min Act: -0.1700
Data Index: 4820515 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.3867. Min Act: -0.1700
Data Index: 6462359 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.4179. Min Act: -0.1700
Data Index: 1273898 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1054. Min Range: -6.1054
Max Act: 5.4179. Min Act: -0.1700
Data Index: 4689675 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19