Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2907 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.8464. Min Act: -0.1700
Data Index: 3630212 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.7839. Min Act: -0.1700
Data Index: 1767877 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.7527. Min Act: -0.1700
Data Index: 6983821 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.7527. Min Act: -0.1700
Data Index: 2262131 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.6902. Min Act: -0.1700
Data Index: 1706974 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.6589. Min Act: -0.1700
Data Index: 4578186 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.6277. Min Act: -0.1700
Data Index: 630685 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.6277. Min Act: -0.1700
Data Index: 5468098 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.5652. Min Act: -0.1700
Data Index: 4693623 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.5027. Min Act: -0.1700
Data Index: 7913486 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.5027. Min Act: -0.1700
Data Index: 7428314 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.4714. Min Act: -0.1700
Data Index: 2316598 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.5027. Min Act: -0.1700
Data Index: 4841570 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.4402. Min Act: -0.1700
Data Index: 8762985 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.4714. Min Act: -0.1700
Data Index: 7620203 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.4402. Min Act: -0.1700
Data Index: 2043595 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.4402. Min Act: -0.1700
Data Index: 56478 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.3777. Min Act: -0.1700
Data Index: 1400833 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.4089. Min Act: -0.1700
Data Index: 3573534 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8464. Min Range: -6.8464
Max Act: 6.4089. Min Act: -0.1700
Data Index: 739045 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19