Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1706 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2518. Min Range: -4.2518
Max Act: 4.2518. Min Act: -0.1700
Data Index: 8394972 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2518. Min Range: -4.2518
Max Act: 4.1893. Min Act: -0.1700
Data Index: 8615813 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2518. Min Range: -4.2518
Max Act: 4.2205. Min Act: -0.1700
Data Index: 2471721 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2518. Min Range: -4.2518
Max Act: 4.1580. Min Act: -0.1700
Data Index: 6551551 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2518. Min Range: -4.2518
Max Act: 4.0642. Min Act: -0.1700
Data Index: 598621 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2518. Min Range: -4.2518
Max Act: 4.0955. Min Act: -0.1700
Data Index: 4573661 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2518. Min Range: -4.2518
Max Act: 4.0486. Min Act: -0.1700
Data Index: 778925 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2518. Min Range: -4.2518
Max Act: 4.0174. Min Act: -0.1700
Data Index: 320583 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2518. Min Range: -4.2518
Max Act: 4.0174. Min Act: -0.1700
Data Index: 4821463 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2518. Min Range: -4.2518
Max Act: 4.0017. Min Act: -0.1700
Data Index: 700398 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2518. Min Range: -4.2518
Max Act: 4.0017. Min Act: -0.1700
Data Index: 4047866 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2518. Min Range: -4.2518
Max Act: 4.0017. Min Act: -0.1700
Data Index: 6489695 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2518. Min Range: -4.2518
Max Act: 4.0174. Min Act: -0.1700
Data Index: 4057194 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2518. Min Range: -4.2518
Max Act: 3.9705. Min Act: -0.1700
Data Index: 3859469 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2518. Min Range: -4.2518
Max Act: 3.9392. Min Act: -0.1700
Data Index: 2148310 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2518. Min Range: -4.2518
Max Act: 3.9705. Min Act: -0.1700
Data Index: 6203353 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2518. Min Range: -4.2518
Max Act: 3.9861. Min Act: -0.1700
Data Index: 6348904 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2518. Min Range: -4.2518
Max Act: 3.9548. Min Act: -0.1700
Data Index: 3070625 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2518. Min Range: -4.2518
Max Act: 3.9548. Min Act: -0.1700
Data Index: 3749406 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2518. Min Range: -4.2518
Max Act: 3.9392. Min Act: -0.1700
Data Index: 2540050 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19