Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.8977. Min Act: -0.1700
Data Index: 335458 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.8352. Min Act: -0.1700
Data Index: 7487022 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.8352. Min Act: -0.1700
Data Index: 695892 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.6477. Min Act: -0.1700
Data Index: 7037954 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.6164. Min Act: -0.1700
Data Index: 7527137 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.6164. Min Act: -0.1700
Data Index: 4926900 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.5852. Min Act: -0.1700
Data Index: 6640224 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.5227. Min Act: -0.1700
Data Index: 7073210 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.4602. Min Act: -0.1700
Data Index: 1092393 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.3977. Min Act: -0.1700
Data Index: 4228600 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.4289. Min Act: -0.1700
Data Index: 3021734 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.4289. Min Act: -0.1700
Data Index: 4882415 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.3664. Min Act: -0.1700
Data Index: 6483712 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.3039. Min Act: -0.1700
Data Index: 2669401 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.3039. Min Act: -0.1700
Data Index: 4033070 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.3039. Min Act: -0.1700
Data Index: 8383362 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.3039. Min Act: -0.1700
Data Index: 3962963 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.2727. Min Act: -0.1700
Data Index: 4863441 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.2102. Min Act: -0.1700
Data Index: 6981801 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8977. Min Range: -7.8977
Max Act: 7.2102. Min Act: -0.1700
Data Index: 2914209 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19