Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3017. Min Range: -2.3017
Max Act: 2.3017. Min Act: -0.1700
Data Index: 4663452 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3017. Min Range: -2.3017
Max Act: 2.0691. Min Act: -0.1700
Data Index: 3864670 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3017. Min Range: -2.3017
Max Act: 2.1026. Min Act: -0.1700
Data Index: 956932 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3017. Min Range: -2.3017
Max Act: 2.0523. Min Act: -0.1697
Data Index: 3905982 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3017. Min Range: -2.3017
Max Act: 2.0355. Min Act: -0.1700
Data Index: 1624042 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3017. Min Range: -2.3017
Max Act: 2.0186. Min Act: -0.1700
Data Index: 5375363 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3017. Min Range: -2.3017
Max Act: 2.0186. Min Act: -0.1700
Data Index: 7825624 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3017. Min Range: -2.3017
Max Act: 2.0355. Min Act: -0.1700
Data Index: 4687646 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3017. Min Range: -2.3017
Max Act: 2.0017. Min Act: -0.1700
Data Index: 211998 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3017. Min Range: -2.3017
Max Act: 2.0186. Min Act: -0.1700
Data Index: 7075711 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3017. Min Range: -2.3017
Max Act: 2.0017. Min Act: -0.1700
Data Index: 8511624 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3017. Min Range: -2.3017
Max Act: 2.0017. Min Act: -0.1700
Data Index: 1966045 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3017. Min Range: -2.3017
Max Act: 1.9679. Min Act: -0.1700
Data Index: 8566482 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3017. Min Range: -2.3017
Max Act: 1.9679. Min Act: -0.1700
Data Index: 7801299 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3017. Min Range: -2.3017
Max Act: 1.9848. Min Act: -0.1700
Data Index: 6517307 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3017. Min Range: -2.3017
Max Act: 1.9848. Min Act: -0.1700
Data Index: 6616883 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3017. Min Range: -2.3017
Max Act: 1.9848. Min Act: -0.1700
Data Index: 169898 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3017. Min Range: -2.3017
Max Act: 1.9848. Min Act: -0.1700
Data Index: 4353138 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3017. Min Range: -2.3017
Max Act: 1.9679. Min Act: -0.1700
Data Index: 6771099 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3017. Min Range: -2.3017
Max Act: 1.9679. Min Act: -0.1700
Data Index: 3254756 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19