Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2376 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.2619. Min Act: -0.1700
Data Index: 3478162 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.1994. Min Act: -0.1700
Data Index: 1381281 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.1994. Min Act: -0.1700
Data Index: 8387608 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.1681. Min Act: -0.1700
Data Index: 6657357 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.1681. Min Act: -0.1700
Data Index: 240407 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.1369. Min Act: -0.1700
Data Index: 5846765 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.1369. Min Act: -0.1700
Data Index: 3478161 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.0744. Min Act: -0.1700
Data Index: 6944799 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.1056. Min Act: -0.1700
Data Index: 18511 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.0744. Min Act: -0.1700
Data Index: 2777807 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.0744. Min Act: -0.1700
Data Index: 6109630 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.0744. Min Act: -0.1700
Data Index: 431005 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.0431. Min Act: -0.1700
Data Index: 4810805 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.0119. Min Act: -0.1700
Data Index: 4570530 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.0119. Min Act: -0.1700
Data Index: 8719236 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.0119. Min Act: -0.1700
Data Index: 6833172 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.0119. Min Act: -0.1700
Data Index: 2777806 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2619. Min Range: -6.2619
Max Act: 6.0119. Min Act: -0.1700
Data Index: 2174258 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2619. Min Range: -6.2619
Max Act: 5.9806. Min Act: -0.1700
Data Index: 18510 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2619. Min Range: -6.2619
Max Act: 5.9806. Min Act: -0.1700
Data Index: 1742313 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19