Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3522 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.2885. Min Act: -0.1700
Data Index: 32442 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.2572. Min Act: -0.1700
Data Index: 4608416 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.1947. Min Act: -0.1700
Data Index: 803814 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.1635. Min Act: -0.1700
Data Index: 1925933 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.1322. Min Act: -0.1700
Data Index: 6006010 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.1322. Min Act: -0.1700
Data Index: 7528804 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.1635. Min Act: -0.1700
Data Index: 4851735 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.0697. Min Act: -0.1700
Data Index: 640078 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.1010. Min Act: -0.1700
Data Index: 5701362 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.1010. Min Act: -0.1700
Data Index: 5370606 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.1010. Min Act: -0.1700
Data Index: 6448753 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.0385. Min Act: -0.1700
Data Index: 7737593 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.0697. Min Act: -0.1700
Data Index: 8526301 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.0385. Min Act: -0.1700
Data Index: 3469497 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.0385. Min Act: -0.1700
Data Index: 6553387 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.0697. Min Act: -0.1700
Data Index: 6838820 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2885. Min Range: -7.2885
Max Act: 7.0072. Min Act: -0.1700
Data Index: 3927834 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2885. Min Range: -7.2885
Max Act: 6.9760. Min Act: -0.1700
Data Index: 2945825 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2885. Min Range: -7.2885
Max Act: 6.9447. Min Act: -0.1700
Data Index: 7354560 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2885. Min Range: -7.2885
Max Act: 6.9447. Min Act: -0.1700
Data Index: 4874272 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19