Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 965 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.6339. Min Act: -0.1700
Data Index: 3710889 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.4464. Min Act: -0.1700
Data Index: 3344010 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.3839. Min Act: -0.1700
Data Index: 2375694 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.3839. Min Act: -0.1700
Data Index: 6070514 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.3214. Min Act: -0.1700
Data Index: 6796472 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.2589. Min Act: -0.1700
Data Index: 5956765 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1964. Min Act: -0.1700
Data Index: 5546524 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1964. Min Act: -0.1700
Data Index: 5890567 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.0714. Min Act: -0.1700
Data Index: 7209934 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1964. Min Act: -0.1700
Data Index: 6339473 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1339. Min Act: -0.1700
Data Index: 3167720 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1339. Min Act: -0.1700
Data Index: 91128 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1339. Min Act: -0.1700
Data Index: 982891 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1339. Min Act: -0.1700
Data Index: 5945480 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.0714. Min Act: -0.1700
Data Index: 3722830 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1339. Min Act: -0.1700
Data Index: 1865359 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.0714. Min Act: -0.1700
Data Index: 6101205 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.0714. Min Act: -0.1700
Data Index: 360130 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.0714. Min Act: -0.1700
Data Index: 6519473 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.0714. Min Act: -0.1700
Data Index: 383032 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19