Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 826 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.6088. Min Act: -0.1700
Data Index: 5991079 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.4526. Min Act: -0.1700
Data Index: 1831774 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.3901. Min Act: -0.1700
Data Index: 5357194 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.3588. Min Act: -0.1700
Data Index: 4811951 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.2963. Min Act: -0.1700
Data Index: 4958015 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.2963. Min Act: -0.1700
Data Index: 5737833 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.2026. Min Act: -0.1700
Data Index: 6268969 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.2026. Min Act: -0.1700
Data Index: 7547079 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.1713. Min Act: -0.1700
Data Index: 5102123 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.1713. Min Act: -0.1700
Data Index: 5349111 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.1713. Min Act: -0.1700
Data Index: 7780382 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.1401. Min Act: -0.1700
Data Index: 4691970 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.1088. Min Act: -0.1700
Data Index: 7653480 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.0776. Min Act: -0.1700
Data Index: 3110258 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.0463. Min Act: -0.1700
Data Index: 4925201 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.0776. Min Act: -0.1700
Data Index: 4098488 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.0463. Min Act: -0.1700
Data Index: 7340386 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.0463. Min Act: -0.1700
Data Index: 6420011 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.0151. Min Act: -0.1700
Data Index: 734917 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6088. Min Range: -7.6088
Max Act: 7.0151. Min Act: -0.1700
Data Index: 483324 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19