Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1219 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.0837. Min Range: -12.0837
Max Act: 12.0212. Min Act: -0.1699
Data Index: 2639045 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0837. Min Range: -12.0837
Max Act: 10.6462. Min Act: -0.1700
Data Index: 44276 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0837. Min Range: -12.0837
Max Act: 10.8337. Min Act: -0.1697
Data Index: 840405 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0837. Min Range: -12.0837
Max Act: 8.2087. Min Act: -0.1700
Data Index: 6701083 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0837. Min Range: -12.0837
Max Act: 6.6149. Min Act: -0.1700
Data Index: 4781515 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0837. Min Range: -12.0837
Max Act: 12.0837. Min Act: -0.1700
Data Index: 4370222 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0837. Min Range: -12.0837
Max Act: 10.3962. Min Act: -0.1700
Data Index: 6649151 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0837. Min Range: -12.0837
Max Act: 9.1462. Min Act: -0.1700
Data Index: 7506025 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0837. Min Range: -12.0837
Max Act: 11.8962. Min Act: -0.1700
Data Index: 2387570 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0837. Min Range: -12.0837
Max Act: 10.2712. Min Act: -0.1700
Data Index: 5989823 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0837. Min Range: -12.0837
Max Act: 10.5837. Min Act: -0.1700
Data Index: 6287338 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0837. Min Range: -12.0837
Max Act: 11.0212. Min Act: -0.1700
Data Index: 6649162 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0837. Min Range: -12.0837
Max Act: 6.3649. Min Act: -0.1700
Data Index: 1987918 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0837. Min Range: -12.0837
Max Act: 9.7087. Min Act: -0.1700
Data Index: 7827976 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0837. Min Range: -12.0837
Max Act: 10.8962. Min Act: -0.1700
Data Index: 5807952 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0837. Min Range: -12.0837
Max Act: 6.8649. Min Act: -0.1699
Data Index: 1088129 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0837. Min Range: -12.0837
Max Act: 10.5212. Min Act: -0.1700
Data Index: 882111 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0837. Min Range: -12.0837
Max Act: 10.3962. Min Act: -0.1700
Data Index: 3145410 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0837. Min Range: -12.0837
Max Act: 9.3962. Min Act: -0.1700
Data Index: 5076413 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0837. Min Range: -12.0837
Max Act: 11.0212. Min Act: -0.1700
Data Index: 2755684 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19