Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4481 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.4977. Min Act: -0.1700
Data Index: 4511874 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.4820. Min Act: -0.1700
Data Index: 8002051 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.4664. Min Act: -0.1700
Data Index: 4000039 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.4350. Min Act: -0.1700
Data Index: 6810827 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.4350. Min Act: -0.1700
Data Index: 6020320 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.3723. Min Act: -0.1700
Data Index: 8563788 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.3566. Min Act: -0.1700
Data Index: 2905854 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.3409. Min Act: -0.1700
Data Index: 4207737 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.3252. Min Act: -0.1700
Data Index: 8598318 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.3095. Min Act: -0.1700
Data Index: 3479018 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.2938. Min Act: -0.1700
Data Index: 4778775 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.2938. Min Act: -0.1700
Data Index: 4283142 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.2781. Min Act: -0.1700
Data Index: 6049554 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.2624. Min Act: -0.1700
Data Index: 5052401 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.2624. Min Act: -0.1700
Data Index: 3019825 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.2467. Min Act: -0.1700
Data Index: 3961310 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.2624. Min Act: -0.1700
Data Index: 5202489 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.2467. Min Act: -0.1700
Data Index: 779413 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.2624. Min Act: -0.1700
Data Index: 35874 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4977. Min Range: -3.4977
Max Act: 3.2467. Min Act: -0.1700
Data Index: 6743718 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19