Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2124 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1068. Min Range: -8.1068
Max Act: 8.1068. Min Act: -0.1700
Data Index: 4997675 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1068. Min Range: -8.1068
Max Act: 8.0131. Min Act: -0.1700
Data Index: 625842 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.9193. Min Act: -0.1700
Data Index: 8290491 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.7631. Min Act: -0.1700
Data Index: 5369222 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.7006. Min Act: -0.1700
Data Index: 8682555 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.7318. Min Act: -0.1700
Data Index: 562003 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.6693. Min Act: -0.1700
Data Index: 1521488 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.6381. Min Act: -0.1700
Data Index: 4846717 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.5443. Min Act: -0.1700
Data Index: 2307125 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.5131. Min Act: -0.1700
Data Index: 7619021 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.5443. Min Act: -0.1700
Data Index: 5794949 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.4818. Min Act: -0.1700
Data Index: 3071637 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.4818. Min Act: -0.1700
Data Index: 1762772 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.4506. Min Act: -0.1700
Data Index: 6008966 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.4506. Min Act: -0.1700
Data Index: 5121789 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.3881. Min Act: -0.1700
Data Index: 6743609 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.4193. Min Act: -0.1700
Data Index: 3241221 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.3881. Min Act: -0.1700
Data Index: 2468216 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.3881. Min Act: -0.1700
Data Index: 824469 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1068. Min Range: -8.1068
Max Act: 7.3881. Min Act: -0.1700
Data Index: 1683861 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19