Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1526 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.8365. Min Act: -0.1700
Data Index: 8670815 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.8365. Min Act: -0.1700
Data Index: 5104261 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.7428. Min Act: -0.1700
Data Index: 7260498 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.5553. Min Act: -0.1700
Data Index: 1861658 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.4303. Min Act: -0.1700
Data Index: 6351868 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.4303. Min Act: -0.1700
Data Index: 4575703 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.3990. Min Act: -0.1700
Data Index: 5559809 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.3678. Min Act: -0.1700
Data Index: 658121 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.3678. Min Act: -0.1700
Data Index: 8774391 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.3678. Min Act: -0.1700
Data Index: 3769277 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.3365. Min Act: -0.1700
Data Index: 7079491 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.3365. Min Act: -0.1700
Data Index: 97376 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.3365. Min Act: -0.1700
Data Index: 1052688 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.3365. Min Act: -0.1700
Data Index: 102060 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.3365. Min Act: -0.1700
Data Index: 3136943 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.2740. Min Act: -0.1700
Data Index: 4725026 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.3053. Min Act: -0.1700
Data Index: 1636371 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.3053. Min Act: -0.1700
Data Index: 5068132 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.3053. Min Act: -0.1700
Data Index: 4780379 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8365. Min Range: -5.8365
Max Act: 5.2740. Min Act: -0.1700
Data Index: 5466344 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19