Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0339. Min Range: -8.0339
Max Act: 8.0339. Min Act: -0.1700
Data Index: 402164 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0339. Min Range: -8.0339
Max Act: 8.0339. Min Act: -0.1700
Data Index: 2863260 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0339. Min Range: -8.0339
Max Act: 8.0339. Min Act: -0.1700
Data Index: 1323807 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0339. Min Range: -8.0339
Max Act: 8.0026. Min Act: -0.1700
Data Index: 7071558 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.9401. Min Act: -0.1700
Data Index: 6721355 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.7839. Min Act: -0.1700
Data Index: 2030753 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.7214. Min Act: -0.1700
Data Index: 7576119 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.6589. Min Act: -0.1700
Data Index: 4596699 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.6276. Min Act: -0.1700
Data Index: 2872951 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.5964. Min Act: -0.1700
Data Index: 4177860 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.5964. Min Act: -0.1700
Data Index: 6092844 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.5026. Min Act: -0.1700
Data Index: 3572003 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.5339. Min Act: -0.1700
Data Index: 3804782 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.5339. Min Act: -0.1700
Data Index: 7304071 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.5026. Min Act: -0.1700
Data Index: 7009523 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.5026. Min Act: -0.1700
Data Index: 6397372 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.4714. Min Act: -0.1700
Data Index: 2609170 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.4401. Min Act: -0.1700
Data Index: 6093572 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.4089. Min Act: -0.1700
Data Index: 402163 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0339. Min Range: -8.0339
Max Act: 7.4401. Min Act: -0.1700
Data Index: 827070 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19