Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 871 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.4207. Min Act: -0.1700
Data Index: 106527 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.3894. Min Act: -0.1700
Data Index: 1125777 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.3737. Min Act: -0.1700
Data Index: 2451852 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.3737. Min Act: -0.1700
Data Index: 1241353 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.3737. Min Act: -0.1700
Data Index: 7654931 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2795. Min Act: -0.1700
Data Index: 155573 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2952. Min Act: -0.1700
Data Index: 44089 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2952. Min Act: -0.1700
Data Index: 127351 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2795. Min Act: -0.1700
Data Index: 123329 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2952. Min Act: -0.1700
Data Index: 8045112 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2324. Min Act: -0.1700
Data Index: 3585832 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2324. Min Act: -0.1700
Data Index: 4022346 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2010. Min Act: -0.1700
Data Index: 2662645 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2638. Min Act: -0.1700
Data Index: 6761229 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2167. Min Act: -0.1700
Data Index: 7818006 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2324. Min Act: -0.1700
Data Index: 5230223 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2324. Min Act: -0.1700
Data Index: 776434 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2324. Min Act: -0.1700
Data Index: 1902601 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.2010. Min Act: -0.1700
Data Index: 7099418 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4207. Min Range: -3.4207
Max Act: 3.3109. Min Act: -0.1700
Data Index: 4956901 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19