Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3265 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3409. Min Range: -8.3409
Max Act: 8.3409. Min Act: -0.1700
Data Index: 1796422 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3409. Min Range: -8.3409
Max Act: 8.3409. Min Act: -0.1700
Data Index: 7464570 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3409. Min Range: -8.3409
Max Act: 8.1534. Min Act: -0.1700
Data Index: 3643906 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3409. Min Range: -8.3409
Max Act: 8.1534. Min Act: -0.1700
Data Index: 4471071 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3409. Min Range: -8.3409
Max Act: 8.0597. Min Act: -0.1700
Data Index: 1696416 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3409. Min Range: -8.3409
Max Act: 8.0597. Min Act: -0.1700
Data Index: 6447934 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3409. Min Range: -8.3409
Max Act: 8.0597. Min Act: -0.1700
Data Index: 1795127 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3409. Min Range: -8.3409
Max Act: 8.0597. Min Act: -0.1700
Data Index: 6472658 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3409. Min Range: -8.3409
Max Act: 8.0597. Min Act: -0.1700
Data Index: 3696313 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3409. Min Range: -8.3409
Max Act: 8.0284. Min Act: -0.1700
Data Index: 6185811 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3409. Min Range: -8.3409
Max Act: 8.0284. Min Act: -0.1700
Data Index: 3525170 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3409. Min Range: -8.3409
Max Act: 7.9659. Min Act: -0.1700
Data Index: 4898488 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3409. Min Range: -8.3409
Max Act: 7.8409. Min Act: -0.1700
Data Index: 4199507 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3409. Min Range: -8.3409
Max Act: 7.8722. Min Act: -0.1700
Data Index: 6845745 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3409. Min Range: -8.3409
Max Act: 7.7784. Min Act: -0.1700
Data Index: 2115886 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3409. Min Range: -8.3409
Max Act: 7.8097. Min Act: -0.1700
Data Index: 4034225 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3409. Min Range: -8.3409
Max Act: 7.7784. Min Act: -0.1700
Data Index: 6953291 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3409. Min Range: -8.3409
Max Act: 7.7784. Min Act: -0.1700
Data Index: 6547503 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3409. Min Range: -8.3409
Max Act: 7.7784. Min Act: -0.1700
Data Index: 5443914 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3409. Min Range: -8.3409
Max Act: 7.7784. Min Act: -0.1700
Data Index: 7524771 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19