Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 976 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.6036. Min Act: -0.1700
Data Index: 8168880 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.5724. Min Act: -0.1700
Data Index: 8254274 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.4786. Min Act: -0.1700
Data Index: 4198052 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.4161. Min Act: -0.1700
Data Index: 4857645 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.3224. Min Act: -0.1700
Data Index: 974600 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.3224. Min Act: -0.1700
Data Index: 4725140 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.2911. Min Act: -0.1700
Data Index: 4092543 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.2599. Min Act: -0.1700
Data Index: 5691554 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.2599. Min Act: -0.1700
Data Index: 2349801 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.2286. Min Act: -0.1700
Data Index: 6213936 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.2286. Min Act: -0.1700
Data Index: 5052831 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.2599. Min Act: -0.1700
Data Index: 4163034 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.1661. Min Act: -0.1700
Data Index: 823163 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.1974. Min Act: -0.1700
Data Index: 2633914 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.1974. Min Act: -0.1700
Data Index: 6832241 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.2286. Min Act: -0.1700
Data Index: 4018440 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.1661. Min Act: -0.1700
Data Index: 3518200 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.1661. Min Act: -0.1700
Data Index: 639802 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.1661. Min Act: -0.1700
Data Index: 6028762 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6036. Min Range: -6.6036
Max Act: 6.1661. Min Act: -0.1700
Data Index: 3102728 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19