Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3739 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.3069. Min Act: -0.1700
Data Index: 553532 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.2757. Min Act: -0.1700
Data Index: 428969 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.2444. Min Act: -0.1700
Data Index: 4942973 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.2444. Min Act: -0.1700
Data Index: 8054307 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.1819. Min Act: -0.1700
Data Index: 8673352 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.1507. Min Act: -0.1700
Data Index: 8673348 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.1507. Min Act: -0.1700
Data Index: 2829085 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.1507. Min Act: -0.1700
Data Index: 3515967 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.1194. Min Act: -0.1700
Data Index: 1773583 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.0882. Min Act: -0.1699
Data Index: 5532084 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.0882. Min Act: -0.1700
Data Index: 8077944 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.0882. Min Act: -0.1700
Data Index: 2866617 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.0882. Min Act: -0.1700
Data Index: 2829084 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.0882. Min Act: -0.1700
Data Index: 3515966 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.0569. Min Act: -0.1700
Data Index: 8673351 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.0569. Min Act: -0.1700
Data Index: 8555765 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.0569. Min Act: -0.1700
Data Index: 4337271 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.0569. Min Act: -0.1700
Data Index: 5972864 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.0257. Min Act: -0.1700
Data Index: 2829086 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3069. Min Range: -5.3069
Max Act: 5.0257. Min Act: -0.1700
Data Index: 3339768 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19