Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.4927. Min Act: -0.1700
Data Index: 6990026 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.4927. Min Act: -0.1700
Data Index: 6800020 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.4927. Min Act: -0.1700
Data Index: 1033288 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.5239. Min Act: -0.1700
Data Index: 1886712 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.4927. Min Act: -0.1700
Data Index: 8183770 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.4927. Min Act: -0.1700
Data Index: 4785578 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.4302. Min Act: -0.1700
Data Index: 2827886 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.4302. Min Act: -0.1700
Data Index: 4019508 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.4302. Min Act: -0.1700
Data Index: 298032 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.3677. Min Act: -0.1700
Data Index: 7638620 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.3677. Min Act: -0.1700
Data Index: 6182096 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.3989. Min Act: -0.1700
Data Index: 6356169 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.3677. Min Act: -0.1700
Data Index: 6990028 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.3989. Min Act: -0.1700
Data Index: 6361984 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.3677. Min Act: -0.1700
Data Index: 6541044 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.3989. Min Act: -0.1700
Data Index: 298034 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.3677. Min Act: -0.1700
Data Index: 5076632 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.3677. Min Act: -0.1700
Data Index: 2827882 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.3364. Min Act: -0.1700
Data Index: 6548150 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5239. Min Range: -7.5239
Max Act: 7.3364. Min Act: -0.1700
Data Index: 2184416 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19