Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5131 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.5330. Min Act: -0.1700
Data Index: 4174868 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.5018. Min Act: -0.1700
Data Index: 4195376 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.4705. Min Act: -0.1700
Data Index: 2817636 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.4705. Min Act: -0.1700
Data Index: 2722125 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.4393. Min Act: -0.1700
Data Index: 3788505 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.4080. Min Act: -0.1700
Data Index: 7699524 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.3455. Min Act: -0.1700
Data Index: 5009913 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.3143. Min Act: -0.1700
Data Index: 3287936 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.2518. Min Act: -0.1700
Data Index: 8645258 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.2205. Min Act: -0.1700
Data Index: 5844786 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.1893. Min Act: -0.1700
Data Index: 7366073 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.1893. Min Act: -0.1700
Data Index: 3125208 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.1893. Min Act: -0.1700
Data Index: 1588671 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.1893. Min Act: -0.1700
Data Index: 3689230 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.1580. Min Act: -0.1700
Data Index: 491563 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.1893. Min Act: -0.1700
Data Index: 7931400 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.1580. Min Act: -0.1700
Data Index: 5871677 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.1268. Min Act: -0.1700
Data Index: 766674 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.1268. Min Act: -0.1700
Data Index: 606357 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5330. Min Range: -6.5330
Max Act: 6.1268. Min Act: -0.1700
Data Index: 8458738 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19