Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 556 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1629. Min Range: -5.1629
Max Act: 5.1629. Min Act: -0.1700
Data Index: 8803725 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.9754. Min Act: -0.1700
Data Index: 2133754 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1629. Min Range: -5.1629
Max Act: 5.0067. Min Act: -0.1700
Data Index: 6762090 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.9442. Min Act: -0.1700
Data Index: 1014646 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.9442. Min Act: -0.1700
Data Index: 2863452 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.9129. Min Act: -0.1700
Data Index: 3826833 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.9129. Min Act: -0.1700
Data Index: 2715619 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.8817. Min Act: -0.1700
Data Index: 5582948 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.8504. Min Act: -0.1700
Data Index: 7000773 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.8504. Min Act: -0.1700
Data Index: 1689475 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.8504. Min Act: -0.1700
Data Index: 2243621 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.8192. Min Act: -0.1700
Data Index: 252694 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.7879. Min Act: -0.1700
Data Index: 4444931 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.7879. Min Act: -0.1700
Data Index: 2296009 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.7567. Min Act: -0.1700
Data Index: 7390740 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.7567. Min Act: -0.1700
Data Index: 5085713 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.7567. Min Act: -0.1700
Data Index: 6011440 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.7567. Min Act: -0.1700
Data Index: 3235722 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.7567. Min Act: -0.1700
Data Index: 4543580 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1629. Min Range: -5.1629
Max Act: 4.7254. Min Act: -0.1700
Data Index: 1293992 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19