Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3954. Min Range: -11.3954
Max Act: 11.3954. Min Act: -0.1700
Data Index: 428637 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3954. Min Range: -11.3954
Max Act: 11.3954. Min Act: -0.1700
Data Index: 8072887 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3954. Min Range: -11.3954
Max Act: 11.2704. Min Act: -0.1700
Data Index: 2705855 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3954. Min Range: -11.3954
Max Act: 11.2079. Min Act: -0.1700
Data Index: 3058407 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3954. Min Range: -11.3954
Max Act: 11.1454. Min Act: -0.1700
Data Index: 6922500 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3954. Min Range: -11.3954
Max Act: 11.1454. Min Act: -0.1700
Data Index: 6232118 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3954. Min Range: -11.3954
Max Act: 11.0829. Min Act: -0.1700
Data Index: 6814849 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3954. Min Range: -11.3954
Max Act: 11.0829. Min Act: -0.1700
Data Index: 2392980 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3954. Min Range: -11.3954
Max Act: 10.9579. Min Act: -0.1700
Data Index: 7419986 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3954. Min Range: -11.3954
Max Act: 10.8954. Min Act: -0.1700
Data Index: 1719875 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3954. Min Range: -11.3954
Max Act: 10.8954. Min Act: -0.1700
Data Index: 7606363 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3954. Min Range: -11.3954
Max Act: 10.8329. Min Act: -0.1700
Data Index: 3672049 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3954. Min Range: -11.3954
Max Act: 10.7704. Min Act: -0.1700
Data Index: 2223432 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3954. Min Range: -11.3954
Max Act: 10.7704. Min Act: -0.1700
Data Index: 3800379 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3954. Min Range: -11.3954
Max Act: 10.7704. Min Act: -0.1700
Data Index: 5655640 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3954. Min Range: -11.3954
Max Act: 10.7704. Min Act: -0.1700
Data Index: 1242017 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3954. Min Range: -11.3954
Max Act: 10.7704. Min Act: -0.1700
Data Index: 17514 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3954. Min Range: -11.3954
Max Act: 10.6454. Min Act: -0.1700
Data Index: 7964250 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3954. Min Range: -11.3954
Max Act: 10.6454. Min Act: -0.1700
Data Index: 7773454 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3954. Min Range: -11.3954
Max Act: 10.6454. Min Act: -0.1700
Data Index: 1708808 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19