Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 264 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2374. Min Range: -7.2374
Max Act: 7.2374. Min Act: -0.1700
Data Index: 5532319 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2374. Min Range: -7.2374
Max Act: 7.2374. Min Act: -0.1700
Data Index: 8514703 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2374. Min Range: -7.2374
Max Act: 7.1749. Min Act: -0.1700
Data Index: 3028172 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2374. Min Range: -7.2374
Max Act: 7.1436. Min Act: -0.1700
Data Index: 8057993 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2374. Min Range: -7.2374
Max Act: 7.0186. Min Act: -0.1700
Data Index: 1177998 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2374. Min Range: -7.2374
Max Act: 7.0186. Min Act: -0.1700
Data Index: 5321072 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.9561. Min Act: -0.1700
Data Index: 5792556 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.9249. Min Act: -0.1700
Data Index: 1234915 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.9561. Min Act: -0.1700
Data Index: 1881862 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.9249. Min Act: -0.1700
Data Index: 8031299 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.9249. Min Act: -0.1700
Data Index: 4820108 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.9249. Min Act: -0.1700
Data Index: 3743808 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.8936. Min Act: -0.1700
Data Index: 2810376 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.9249. Min Act: -0.1700
Data Index: 2936927 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.8311. Min Act: -0.1700
Data Index: 3631776 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.7686. Min Act: -0.1700
Data Index: 728671 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.7374. Min Act: -0.1700
Data Index: 2243113 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.7061. Min Act: -0.1700
Data Index: 3428100 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.6749. Min Act: -0.1700
Data Index: 5296543 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2374. Min Range: -7.2374
Max Act: 6.6749. Min Act: -0.1700
Data Index: 97556 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19