Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1428 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1303. Min Range: -6.1303
Max Act: 6.1303. Min Act: -0.1700
Data Index: 7103777 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1303. Min Range: -6.1303
Max Act: 6.0678. Min Act: -0.1700
Data Index: 8084041 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1303. Min Range: -6.1303
Max Act: 6.0053. Min Act: -0.1700
Data Index: 4535978 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1303. Min Range: -6.1303
Max Act: 6.0053. Min Act: -0.1700
Data Index: 5677158 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.9741. Min Act: -0.1700
Data Index: 4035301 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.9428. Min Act: -0.1700
Data Index: 1315121 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.9116. Min Act: -0.1700
Data Index: 6739611 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.9116. Min Act: -0.1700
Data Index: 7060682 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.8803. Min Act: -0.1700
Data Index: 1024855 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.8803. Min Act: -0.1700
Data Index: 7525472 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.8803. Min Act: -0.1700
Data Index: 8456198 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.8803. Min Act: -0.1700
Data Index: 1770873 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.8803. Min Act: -0.1700
Data Index: 1987161 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.8491. Min Act: -0.1700
Data Index: 6022233 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.8491. Min Act: -0.1700
Data Index: 6324269 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.8178. Min Act: -0.1700
Data Index: 3191863 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.8178. Min Act: -0.1700
Data Index: 5648935 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.8178. Min Act: -0.1700
Data Index: 1931081 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.8178. Min Act: -0.1700
Data Index: 2985269 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1303. Min Range: -6.1303
Max Act: 5.7866. Min Act: -0.1700
Data Index: 4751354 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19