Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 535 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1616. Min Act: -0.1700
Data Index: 8038096 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1459. Min Act: -0.1700
Data Index: 2581529 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1459. Min Act: -0.1700
Data Index: 2005144 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1459. Min Act: -0.1700
Data Index: 5927627 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1459. Min Act: -0.1700
Data Index: 7097868 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1301. Min Act: -0.1700
Data Index: 2605864 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1301. Min Act: -0.1700
Data Index: 1391326 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1301. Min Act: -0.1700
Data Index: 3593640 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1301. Min Act: -0.1700
Data Index: 5046968 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1144. Min Act: -0.1700
Data Index: 3474217 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1144. Min Act: -0.1700
Data Index: 7725837 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1144. Min Act: -0.1700
Data Index: 4758724 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1144. Min Act: -0.1700
Data Index: 5211743 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1144. Min Act: -0.1700
Data Index: 621909 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1144. Min Act: -0.1700
Data Index: 3825991 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1144. Min Act: -0.1700
Data Index: 912286 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.1144. Min Act: -0.1700
Data Index: 4947649 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.0986. Min Act: -0.1700
Data Index: 1374928 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.0986. Min Act: -0.1700
Data Index: 1447013 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1616. Min Range: -3.1616
Max Act: 3.0986. Min Act: -0.1700
Data Index: 4054896 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19