Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2503 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.6036. Min Range: -9.6036
Max Act: 9.6036. Min Act: -0.1700
Data Index: 4775064 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6036. Min Range: -9.6036
Max Act: 9.4161. Min Act: -0.1700
Data Index: 5534551 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6036. Min Range: -9.6036
Max Act: 9.4786. Min Act: -0.1700
Data Index: 1363848 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6036. Min Range: -9.6036
Max Act: 9.2911. Min Act: -0.1700
Data Index: 8690030 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6036. Min Range: -9.6036
Max Act: 9.0411. Min Act: -0.1700
Data Index: 2746179 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6036. Min Range: -9.6036
Max Act: 9.0411. Min Act: -0.1700
Data Index: 3673463 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.9786. Min Act: -0.1700
Data Index: 2811152 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.8536. Min Act: -0.1700
Data Index: 655326 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.9161. Min Act: -0.1700
Data Index: 8175245 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.7911. Min Act: -0.1700
Data Index: 8493706 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.7911. Min Act: -0.1700
Data Index: 4749423 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.9161. Min Act: -0.1700
Data Index: 486315 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.8536. Min Act: -0.1700
Data Index: 5404173 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.8536. Min Act: -0.1700
Data Index: 6741053 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.8536. Min Act: -0.1700
Data Index: 6881301 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.8536. Min Act: -0.1700
Data Index: 8536394 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.7911. Min Act: -0.1700
Data Index: 6092340 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.7911. Min Act: -0.1700
Data Index: 1201531 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.7286. Min Act: -0.1700
Data Index: 2028849 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6036. Min Range: -9.6036
Max Act: 8.7286. Min Act: -0.1700
Data Index: 3320645 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19