Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3300 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.0553. Min Range: -15.0553
Max Act: 15.0553. Min Act: -0.1700
Data Index: 5537168 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.0553. Min Range: -15.0553
Max Act: 14.4303. Min Act: -0.1700
Data Index: 5409259 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.0553. Min Range: -15.0553
Max Act: 14.4303. Min Act: -0.1700
Data Index: 732914 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.0553. Min Range: -15.0553
Max Act: 14.3053. Min Act: -0.1700
Data Index: 1236466 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.0553. Min Range: -15.0553
Max Act: 14.3053. Min Act: -0.1700
Data Index: 4948428 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.0553. Min Range: -15.0553
Max Act: 14.2428. Min Act: -0.1700
Data Index: 1269310 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.0553. Min Range: -15.0553
Max Act: 14.1803. Min Act: -0.1700
Data Index: 6256858 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.0553. Min Range: -15.0553
Max Act: 14.1803. Min Act: -0.1700
Data Index: 2052204 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.0553. Min Range: -15.0553
Max Act: 14.1803. Min Act: -0.1700
Data Index: 8274245 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.0553. Min Range: -15.0553
Max Act: 14.1178. Min Act: -0.1700
Data Index: 2551960 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.0553. Min Range: -15.0553
Max Act: 14.0553. Min Act: -0.1700
Data Index: 6064638 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.0553. Min Range: -15.0553
Max Act: 14.0553. Min Act: -0.1700
Data Index: 1269303 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.0553. Min Range: -15.0553
Max Act: 14.0553. Min Act: -0.1700
Data Index: 7000908 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.0553. Min Range: -15.0553
Max Act: 13.9928. Min Act: -0.1700
Data Index: 1884413 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.0553. Min Range: -15.0553
Max Act: 13.9928. Min Act: -0.1700
Data Index: 5537151 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.0553. Min Range: -15.0553
Max Act: 13.9303. Min Act: -0.1700
Data Index: 6810198 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.0553. Min Range: -15.0553
Max Act: 13.8678. Min Act: -0.1700
Data Index: 3626112 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.0553. Min Range: -15.0553
Max Act: 13.8678. Min Act: -0.1700
Data Index: 585712 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.0553. Min Range: -15.0553
Max Act: 13.8678. Min Act: -0.1700
Data Index: 873851 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.0553. Min Range: -15.0553
Max Act: 13.8678. Min Act: -0.1700
Data Index: 4799129 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19