Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 721 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4991. Min Range: -4.4991
Max Act: 4.4991. Min Act: -0.1700
Data Index: 2878371 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4991. Min Range: -4.4991
Max Act: 4.3741. Min Act: -0.1700
Data Index: 2878357 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4991. Min Range: -4.4991
Max Act: 4.2178. Min Act: -0.1700
Data Index: 429503 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4991. Min Range: -4.4991
Max Act: 4.2178. Min Act: -0.1700
Data Index: 2878359 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4991. Min Range: -4.4991
Max Act: 4.1866. Min Act: -0.1700
Data Index: 429499 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4991. Min Range: -4.4991
Max Act: 4.0303. Min Act: -0.1700
Data Index: 5997243 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.9991. Min Act: -0.1700
Data Index: 2878363 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.9678. Min Act: -0.1700
Data Index: 5701146 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.9365. Min Act: -0.1700
Data Index: 7028656 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.9053. Min Act: -0.1700
Data Index: 5499701 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.8740. Min Act: -0.1700
Data Index: 7624591 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.8427. Min Act: -0.1700
Data Index: 429495 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.8427. Min Act: -0.1700
Data Index: 1360284 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.8740. Min Act: -0.1700
Data Index: 6435811 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.8427. Min Act: -0.1700
Data Index: 2561377 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.8271. Min Act: -0.1700
Data Index: 8706669 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.7802. Min Act: -0.1700
Data Index: 6654399 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.7645. Min Act: -0.1700
Data Index: 4958850 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.7645. Min Act: -0.1700
Data Index: 7093205 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4991. Min Range: -4.4991
Max Act: 3.7645. Min Act: -0.1700
Data Index: 5919857 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19