Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2480 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.6552. Min Act: -0.1700
Data Index: 5599221 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.4989. Min Act: -0.1700
Data Index: 4155631 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.4677. Min Act: -0.1700
Data Index: 6922903 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.4052. Min Act: -0.1700
Data Index: 498228 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.3427. Min Act: -0.1700
Data Index: 2698633 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.3114. Min Act: -0.1700
Data Index: 3127734 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.2802. Min Act: -0.1700
Data Index: 2080119 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.2489. Min Act: -0.1700
Data Index: 5766436 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.2177. Min Act: -0.1700
Data Index: 6594635 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.2177. Min Act: -0.1700
Data Index: 2375443 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.1864. Min Act: -0.1700
Data Index: 4618948 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.1864. Min Act: -0.1700
Data Index: 6929634 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.1239. Min Act: -0.1700
Data Index: 150533 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.0927. Min Act: -0.1700
Data Index: 8292255 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.1239. Min Act: -0.1700
Data Index: 671796 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.1552. Min Act: -0.1700
Data Index: 6453510 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.1239. Min Act: -0.1700
Data Index: 1592758 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.1239. Min Act: -0.1700
Data Index: 916581 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.0927. Min Act: -0.1700
Data Index: 277740 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6552. Min Range: -6.6552
Max Act: 6.0927. Min Act: -0.1700
Data Index: 1530179 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19