Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1674 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7935. Min Range: -8.7935
Max Act: 8.7935. Min Act: -0.1700
Data Index: 377793 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7935. Min Range: -8.7935
Max Act: 8.2935. Min Act: -0.1700
Data Index: 4221111 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7935. Min Range: -8.7935
Max Act: 8.1685. Min Act: -0.1700
Data Index: 3879885 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.9497. Min Act: -0.1700
Data Index: 2975031 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.9497. Min Act: -0.1700
Data Index: 9222 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.7935. Min Act: -0.1700
Data Index: 5465930 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.7935. Min Act: -0.1700
Data Index: 6766472 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.7935. Min Act: -0.1700
Data Index: 3151657 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.7310. Min Act: -0.1700
Data Index: 6357969 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.6060. Min Act: -0.1700
Data Index: 8270902 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.5435. Min Act: -0.1700
Data Index: 2283272 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.4810. Min Act: -0.1700
Data Index: 2979549 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.5122. Min Act: -0.1700
Data Index: 8209382 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.4810. Min Act: -0.1700
Data Index: 4010475 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.4497. Min Act: -0.1700
Data Index: 5863673 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.4185. Min Act: -0.1700
Data Index: 1247477 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.4497. Min Act: -0.1700
Data Index: 1399378 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.3560. Min Act: -0.1700
Data Index: 6725856 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.3247. Min Act: -0.1700
Data Index: 5736997 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7935. Min Range: -8.7935
Max Act: 7.3247. Min Act: -0.1700
Data Index: 3844206 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19