Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4890 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5605. Min Range: -9.5605
Max Act: 9.5605. Min Act: -0.1700
Data Index: 4959650 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5605. Min Range: -9.5605
Max Act: 9.4980. Min Act: -0.1700
Data Index: 6945587 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5605. Min Range: -9.5605
Max Act: 9.3105. Min Act: -0.1700
Data Index: 3458475 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5605. Min Range: -9.5605
Max Act: 9.3105. Min Act: -0.1700
Data Index: 3065487 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5605. Min Range: -9.5605
Max Act: 9.2480. Min Act: -0.1700
Data Index: 301632 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5605. Min Range: -9.5605
Max Act: 9.1855. Min Act: -0.1700
Data Index: 7539850 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5605. Min Range: -9.5605
Max Act: 9.0605. Min Act: -0.1700
Data Index: 5477031 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5605. Min Range: -9.5605
Max Act: 8.9980. Min Act: -0.1700
Data Index: 3487864 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5605. Min Range: -9.5605
Max Act: 8.9980. Min Act: -0.1700
Data Index: 7497655 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5605. Min Range: -9.5605
Max Act: 8.9980. Min Act: -0.1700
Data Index: 165348 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5605. Min Range: -9.5605
Max Act: 8.9980. Min Act: -0.1700
Data Index: 7079568 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5605. Min Range: -9.5605
Max Act: 8.9980. Min Act: -0.1700
Data Index: 2323726 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5605. Min Range: -9.5605
Max Act: 8.9980. Min Act: -0.1700
Data Index: 7758332 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5605. Min Range: -9.5605
Max Act: 8.9355. Min Act: -0.1700
Data Index: 2945930 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5605. Min Range: -9.5605
Max Act: 8.9355. Min Act: -0.1700
Data Index: 8549168 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5605. Min Range: -9.5605
Max Act: 8.9355. Min Act: -0.1700
Data Index: 3758241 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5605. Min Range: -9.5605
Max Act: 8.8730. Min Act: -0.1700
Data Index: 2777891 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5605. Min Range: -9.5605
Max Act: 8.8730. Min Act: -0.1700
Data Index: 6506660 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5605. Min Range: -9.5605
Max Act: 8.8730. Min Act: -0.1700
Data Index: 7198398 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5605. Min Range: -9.5605
Max Act: 8.8730. Min Act: -0.1700
Data Index: 1903287 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19