Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3043 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.9584. Min Act: -0.1700
Data Index: 1115744 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.7709. Min Act: -0.1700
Data Index: 5873531 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.7084. Min Act: -0.1700
Data Index: 738936 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.6772. Min Act: -0.1700
Data Index: 3270843 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.6772. Min Act: -0.1700
Data Index: 4271741 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.5522. Min Act: -0.1700
Data Index: 640554 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.5522. Min Act: -0.1700
Data Index: 4244296 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.5209. Min Act: -0.1700
Data Index: 5943712 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.5209. Min Act: -0.1700
Data Index: 3269488 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.5209. Min Act: -0.1700
Data Index: 3474505 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.4897. Min Act: -0.1700
Data Index: 7557171 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.4897. Min Act: -0.1700
Data Index: 1743825 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.4584. Min Act: -0.1700
Data Index: 1349953 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.4897. Min Act: -0.1700
Data Index: 5995059 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.4584. Min Act: -0.1700
Data Index: 8448315 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.4584. Min Act: -0.1700
Data Index: 5154933 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.3959. Min Act: -0.1700
Data Index: 1634829 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.3959. Min Act: -0.1700
Data Index: 2509899 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.4272. Min Act: -0.1700
Data Index: 1663432 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.4272. Min Act: -0.1700
Data Index: 6963988 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19