Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.3930. Min Act: -0.1700
Data Index: 2751039 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.1430. Min Act: -0.1700
Data Index: 5929551 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0805. Min Act: -0.1700
Data Index: 7135969 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.1117. Min Act: -0.1700
Data Index: 4537817 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0805. Min Act: -0.1700
Data Index: 7172091 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0805. Min Act: -0.1700
Data Index: 5736636 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0805. Min Act: -0.1700
Data Index: 4876639 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0805. Min Act: -0.1700
Data Index: 7277496 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0492. Min Act: -0.1700
Data Index: 2864441 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0179. Min Act: -0.1700
Data Index: 660175 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0179. Min Act: -0.1700
Data Index: 7386125 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0492. Min Act: -0.1700
Data Index: 5448540 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0492. Min Act: -0.1700
Data Index: 2472322 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3930. Min Range: -4.3930
Max Act: 3.9867. Min Act: -0.1700
Data Index: 1440678 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0179. Min Act: -0.1700
Data Index: 3968701 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0179. Min Act: -0.1700
Data Index: 2398702 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0179. Min Act: -0.1700
Data Index: 121968 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3930. Min Range: -4.3930
Max Act: 3.9867. Min Act: -0.1700
Data Index: 5433265 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3930. Min Range: -4.3930
Max Act: 3.9554. Min Act: -0.1700
Data Index: 8569533 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.0179. Min Act: -0.1700
Data Index: 6895421 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19