Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1786 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1700. Min Range: -9.1700
Max Act: 9.1700. Min Act: -0.1700
Data Index: 1968909 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1700. Min Range: -9.1700
Max Act: 9.0450. Min Act: -0.1700
Data Index: 8616653 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.9200. Min Act: -0.1700
Data Index: 1016953 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.9200. Min Act: -0.1700
Data Index: 662949 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.8575. Min Act: -0.1700
Data Index: 694994 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.7325. Min Act: -0.1700
Data Index: 584359 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.6075. Min Act: -0.1700
Data Index: 6699630 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.6075. Min Act: -0.1700
Data Index: 4673613 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.6075. Min Act: -0.1700
Data Index: 1689620 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.6075. Min Act: -0.1700
Data Index: 534820 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.4825. Min Act: -0.1700
Data Index: 1708672 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.4825. Min Act: -0.1700
Data Index: 2595381 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.4825. Min Act: -0.1700
Data Index: 4299828 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.4200. Min Act: -0.1700
Data Index: 2593112 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.4200. Min Act: -0.1700
Data Index: 6265875 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.4200. Min Act: -0.1700
Data Index: 2062883 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.4200. Min Act: -0.1700
Data Index: 7970780 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.4200. Min Act: -0.1700
Data Index: 2382351 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.4200. Min Act: -0.1700
Data Index: 5280364 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1700. Min Range: -9.1700
Max Act: 8.2950. Min Act: -0.1700
Data Index: 1848785 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19