Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1779 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.8039. Min Act: -0.1700
Data Index: 4692801 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.7414. Min Act: -0.1700
Data Index: 7009580 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.5539. Min Act: -0.1700
Data Index: 249257 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.5227. Min Act: -0.1700
Data Index: 8370832 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.4914. Min Act: -0.1700
Data Index: 5907665 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.4914. Min Act: -0.1700
Data Index: 6303580 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.4602. Min Act: -0.1700
Data Index: 1262790 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.4602. Min Act: -0.1700
Data Index: 1477352 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.4289. Min Act: -0.1700
Data Index: 2094563 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.3977. Min Act: -0.1700
Data Index: 662871 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.3664. Min Act: -0.1700
Data Index: 1949870 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.3977. Min Act: -0.1700
Data Index: 3477345 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.3664. Min Act: -0.1700
Data Index: 2215546 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.3664. Min Act: -0.1700
Data Index: 2941785 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.3039. Min Act: -0.1700
Data Index: 350884 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.2727. Min Act: -0.1700
Data Index: 8260904 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.2727. Min Act: -0.1700
Data Index: 7748442 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.2102. Min Act: -0.1700
Data Index: 459933 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.2102. Min Act: -0.1700
Data Index: 1614242 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8039. Min Range: -6.8039
Max Act: 6.1789. Min Act: -0.1700
Data Index: 8049644 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19