Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3292 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4938. Min Range: -10.4938
Max Act: 10.4938. Min Act: -0.1700
Data Index: 4119562 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4938. Min Range: -10.4938
Max Act: 10.1813. Min Act: -0.1700
Data Index: 5456085 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.6813. Min Act: -0.1700
Data Index: 6803899 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.5563. Min Act: -0.1700
Data Index: 6648333 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.5563. Min Act: -0.1700
Data Index: 8013518 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.4938. Min Act: -0.1700
Data Index: 44801 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.4938. Min Act: -0.1700
Data Index: 7922502 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.4938. Min Act: -0.1700
Data Index: 785073 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.4313. Min Act: -0.1700
Data Index: 1904895 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.4313. Min Act: -0.1700
Data Index: 2997385 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.4313. Min Act: -0.1700
Data Index: 8045733 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.3688. Min Act: -0.1700
Data Index: 1712394 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.3063. Min Act: -0.1700
Data Index: 2518188 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.3063. Min Act: -0.1700
Data Index: 3017206 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.3063. Min Act: -0.1700
Data Index: 3309923 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.2438. Min Act: -0.1700
Data Index: 8057873 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.2438. Min Act: -0.1700
Data Index: 1689032 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.2438. Min Act: -0.1700
Data Index: 836913 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.2438. Min Act: -0.1700
Data Index: 8291052 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4938. Min Range: -10.4938
Max Act: 9.1813. Min Act: -0.1700
Data Index: 3113132 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19