Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2221 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2791. Min Range: -7.2791
Max Act: 7.2791. Min Act: -0.1700
Data Index: 2716093 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2791. Min Range: -7.2791
Max Act: 7.2479. Min Act: -0.1700
Data Index: 5428306 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2791. Min Range: -7.2791
Max Act: 7.0916. Min Act: -0.1700
Data Index: 368803 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2791. Min Range: -7.2791
Max Act: 7.0291. Min Act: -0.1700
Data Index: 7388482 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2791. Min Range: -7.2791
Max Act: 7.0604. Min Act: -0.1700
Data Index: 7059818 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.9666. Min Act: -0.1700
Data Index: 703785 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.9666. Min Act: -0.1700
Data Index: 2608421 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.9666. Min Act: -0.1700
Data Index: 7261334 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.9354. Min Act: -0.1700
Data Index: 3601623 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.9041. Min Act: -0.1700
Data Index: 7800058 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.9041. Min Act: -0.1700
Data Index: 8571773 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.9041. Min Act: -0.1700
Data Index: 6618097 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.8729. Min Act: -0.1700
Data Index: 8755386 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.9354. Min Act: -0.1700
Data Index: 8818927 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.9041. Min Act: -0.1700
Data Index: 5244823 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.9041. Min Act: -0.1700
Data Index: 5075897 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.9041. Min Act: -0.1700
Data Index: 6774923 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.8729. Min Act: -0.1700
Data Index: 387514 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.8729. Min Act: -0.1700
Data Index: 6774913 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2791. Min Range: -7.2791
Max Act: 6.8729. Min Act: -0.1700
Data Index: 2589982 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19