Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1930 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1114. Min Range: -8.1114
Max Act: 8.1114. Min Act: -0.1700
Data Index: 7289448 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.7052. Min Act: -0.1700
Data Index: 2993089 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.4864. Min Act: -0.1700
Data Index: 7976548 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.3614. Min Act: -0.1700
Data Index: 4173770 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.2989. Min Act: -0.1700
Data Index: 8408317 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.2677. Min Act: -0.1700
Data Index: 5073025 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.2364. Min Act: -0.1700
Data Index: 8200524 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.2677. Min Act: -0.1700
Data Index: 3878111 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.2677. Min Act: -0.1700
Data Index: 2843510 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.2364. Min Act: -0.1700
Data Index: 6938392 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.2364. Min Act: -0.1700
Data Index: 6743260 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.2052. Min Act: -0.1700
Data Index: 170317 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.2052. Min Act: -0.1700
Data Index: 7410565 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.2052. Min Act: -0.1700
Data Index: 1644767 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.1739. Min Act: -0.1700
Data Index: 8094350 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.1739. Min Act: -0.1700
Data Index: 3376255 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.1739. Min Act: -0.1700
Data Index: 929738 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.1739. Min Act: -0.1700
Data Index: 3253520 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.1427. Min Act: -0.1700
Data Index: 2675748 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.1114. Min Act: -0.1700
Data Index: 7461057 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19