Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.5134. Min Act: -0.1700
Data Index: 4524389 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.8884. Min Act: -0.1700
Data Index: 1134308 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.8884. Min Act: -0.1700
Data Index: 7972683 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.6384. Min Act: -0.1700
Data Index: 4226386 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.6384. Min Act: -0.1700
Data Index: 6162146 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.6384. Min Act: -0.1700
Data Index: 1547754 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.5446. Min Act: -0.1700
Data Index: 1237427 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.5759. Min Act: -0.1700
Data Index: 7025646 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.5759. Min Act: -0.1700
Data Index: 3379928 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.5446. Min Act: -0.1700
Data Index: 5076725 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.5446. Min Act: -0.1700
Data Index: 4710275 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.4821. Min Act: -0.1700
Data Index: 2753867 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.4821. Min Act: -0.1700
Data Index: 6173216 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.4821. Min Act: -0.1700
Data Index: 1384444 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.4509. Min Act: -0.1700
Data Index: 4544838 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.3884. Min Act: -0.1700
Data Index: 4205757 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.4196. Min Act: -0.1700
Data Index: 1413710 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.3884. Min Act: -0.1700
Data Index: 2917301 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.3884. Min Act: -0.1700
Data Index: 1637109 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.3571. Min Act: -0.1700
Data Index: 3482613 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19