Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4675 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0594. Min Range: -8.0594
Max Act: 8.0594. Min Act: -0.1700
Data Index: 2683917 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0594. Min Range: -8.0594
Max Act: 7.9657. Min Act: -0.1700
Data Index: 3012509 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0594. Min Range: -8.0594
Max Act: 7.6532. Min Act: -0.1700
Data Index: 3672833 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0594. Min Range: -8.0594
Max Act: 7.2782. Min Act: -0.1700
Data Index: 577338 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0594. Min Range: -8.0594
Max Act: 7.2782. Min Act: -0.1700
Data Index: 7267941 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0594. Min Range: -8.0594
Max Act: 7.0594. Min Act: -0.1700
Data Index: 5830136 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.9657. Min Act: -0.1700
Data Index: 6034599 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.9344. Min Act: -0.1700
Data Index: 2783627 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.8719. Min Act: -0.1700
Data Index: 2611066 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.8407. Min Act: -0.1700
Data Index: 2292972 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.8407. Min Act: -0.1700
Data Index: 1517137 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.8094. Min Act: -0.1700
Data Index: 209419 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.8094. Min Act: -0.1700
Data Index: 5668858 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.8407. Min Act: -0.1700
Data Index: 8219144 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.7469. Min Act: -0.1700
Data Index: 2528517 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.8094. Min Act: -0.1700
Data Index: 3777847 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.7469. Min Act: -0.1700
Data Index: 209430 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.7469. Min Act: -0.1700
Data Index: 4371153 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.7469. Min Act: -0.1700
Data Index: 652647 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0594. Min Range: -8.0594
Max Act: 6.7469. Min Act: -0.1700
Data Index: 896544 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19