Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3307 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.5538. Min Act: -0.1700
Data Index: 1601887 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.5225. Min Act: -0.1700
Data Index: 6566858 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.4913. Min Act: -0.1700
Data Index: 1601899 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.4600. Min Act: -0.1700
Data Index: 1078315 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.4288. Min Act: -0.1700
Data Index: 7931081 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.3975. Min Act: -0.1700
Data Index: 4548104 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.3975. Min Act: -0.1700
Data Index: 7085432 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.3975. Min Act: -0.1700
Data Index: 2356540 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.3975. Min Act: -0.1700
Data Index: 2356521 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.3350. Min Act: -0.1700
Data Index: 3631040 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.3663. Min Act: -0.1700
Data Index: 4264072 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.3663. Min Act: -0.1700
Data Index: 8529162 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.3038. Min Act: -0.1700
Data Index: 5719662 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.3350. Min Act: -0.1700
Data Index: 1957143 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.3350. Min Act: -0.1700
Data Index: 8276078 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.3038. Min Act: -0.1700
Data Index: 1485684 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.3350. Min Act: -0.1700
Data Index: 4139701 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.3038. Min Act: -0.1700
Data Index: 8043402 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.2725. Min Act: -0.1700
Data Index: 5289850 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5538. Min Range: -4.5538
Max Act: 4.2725. Min Act: -0.1700
Data Index: 3340158 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19