Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 551 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1754. Min Range: -5.1754
Max Act: 5.1754. Min Act: -0.1700
Data Index: 2574209 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1754. Min Range: -5.1754
Max Act: 5.1754. Min Act: -0.1700
Data Index: 8651600 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1754. Min Range: -5.1754
Max Act: 5.0191. Min Act: -0.1700
Data Index: 5846219 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.9566. Min Act: -0.1700
Data Index: 1385471 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.9254. Min Act: -0.1700
Data Index: 5846218 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.8629. Min Act: -0.1700
Data Index: 3783555 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.8629. Min Act: -0.1700
Data Index: 2159646 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.8316. Min Act: -0.1700
Data Index: 2660122 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.7691. Min Act: -0.1700
Data Index: 8153172 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.7691. Min Act: -0.1700
Data Index: 226210 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.7691. Min Act: -0.1700
Data Index: 5473625 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.7691. Min Act: -0.1700
Data Index: 8783892 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.7379. Min Act: -0.1700
Data Index: 150884 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.7379. Min Act: -0.1700
Data Index: 4415588 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.7691. Min Act: -0.1700
Data Index: 2131054 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.7066. Min Act: -0.1700
Data Index: 5624664 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.7066. Min Act: -0.1700
Data Index: 8466824 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.6754. Min Act: -0.1700
Data Index: 1162019 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.6754. Min Act: -0.1700
Data Index: 2959205 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1754. Min Range: -5.1754
Max Act: 4.6754. Min Act: -0.1700
Data Index: 3942650 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19