Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3624 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.7832. Min Act: -0.1700
Data Index: 2513305 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.6893. Min Act: -0.1700
Data Index: 1363916 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.6424. Min Act: -0.1700
Data Index: 6454879 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.6111. Min Act: -0.1700
Data Index: 6606200 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.5798. Min Act: -0.1700
Data Index: 6826455 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.5798. Min Act: -0.1700
Data Index: 1973703 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.5485. Min Act: -0.1700
Data Index: 7393951 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.5485. Min Act: -0.1700
Data Index: 1319565 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.5328. Min Act: -0.1700
Data Index: 3657566 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.5015. Min Act: -0.1700
Data Index: 7911850 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.5015. Min Act: -0.1700
Data Index: 5519275 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.4702. Min Act: -0.1700
Data Index: 701236 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.4075. Min Act: -0.1700
Data Index: 5708995 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.4075. Min Act: -0.1700
Data Index: 655821 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.4075. Min Act: -0.1700
Data Index: 6915206 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.3918. Min Act: -0.1700
Data Index: 7005435 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.3918. Min Act: -0.1700
Data Index: 358204 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.3761. Min Act: -0.1700
Data Index: 2911925 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.3761. Min Act: -0.1700
Data Index: 8510527 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7832. Min Range: -3.7832
Max Act: 3.3605. Min Act: -0.1700
Data Index: 2051591 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19