Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.9601. Min Act: -0.1700
Data Index: 6709821 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.8351. Min Act: -0.1700
Data Index: 1696818 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.7726. Min Act: -0.1700
Data Index: 2661176 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.7726. Min Act: -0.1700
Data Index: 6349886 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.7414. Min Act: -0.1700
Data Index: 1634921 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.7101. Min Act: -0.1700
Data Index: 4940912 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.7414. Min Act: -0.1700
Data Index: 3332110 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.7414. Min Act: -0.1700
Data Index: 5745007 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.7101. Min Act: -0.1700
Data Index: 1345437 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.7101. Min Act: -0.1700
Data Index: 8177842 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.7101. Min Act: -0.1700
Data Index: 4266561 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.6789. Min Act: -0.1700
Data Index: 2972697 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.6789. Min Act: -0.1700
Data Index: 5311058 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.6476. Min Act: -0.1700
Data Index: 26312 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.6789. Min Act: -0.1700
Data Index: 3691116 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.6476. Min Act: -0.1700
Data Index: 2735750 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.6164. Min Act: -0.1700
Data Index: 5285077 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.6164. Min Act: -0.1700
Data Index: 5581461 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.6164. Min Act: -0.1700
Data Index: 7990714 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.5851. Min Act: -0.1700
Data Index: 3769467 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19