Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3375 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.7745. Min Act: -0.1700
Data Index: 7696896 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.5557. Min Act: -0.1700
Data Index: 2327956 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.5245. Min Act: -0.1700
Data Index: 2092081 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.4620. Min Act: -0.1700
Data Index: 919874 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.3995. Min Act: -0.1700
Data Index: 723443 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.3995. Min Act: -0.1700
Data Index: 3505565 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.2745. Min Act: -0.1700
Data Index: 6386802 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.3057. Min Act: -0.1700
Data Index: 784986 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.2432. Min Act: -0.1700
Data Index: 2580063 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.2432. Min Act: -0.1700
Data Index: 343293 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.1495. Min Act: -0.1700
Data Index: 8066314 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.1807. Min Act: -0.1700
Data Index: 1308485 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.1495. Min Act: -0.1700
Data Index: 3074596 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.0870. Min Act: -0.1700
Data Index: 5333961 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.0870. Min Act: -0.1700
Data Index: 2481356 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.0245. Min Act: -0.1700
Data Index: 4653580 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7745. Min Range: -7.7745
Max Act: 7.0870. Min Act: -0.1700
Data Index: 3515823 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7745. Min Range: -7.7745
Max Act: 6.9932. Min Act: -0.1700
Data Index: 5953293 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7745. Min Range: -7.7745
Max Act: 6.9620. Min Act: -0.1700
Data Index: 4576022 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7745. Min Range: -7.7745
Max Act: 6.9620. Min Act: -0.1700
Data Index: 2664740 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19