Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2763 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0260. Min Range: -8.0260
Max Act: 8.0260. Min Act: -0.1700
Data Index: 899676 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0260. Min Range: -8.0260
Max Act: 7.6822. Min Act: -0.1700
Data Index: 660988 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0260. Min Range: -8.0260
Max Act: 7.3697. Min Act: -0.1700
Data Index: 8574910 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0260. Min Range: -8.0260
Max Act: 7.2760. Min Act: -0.1700
Data Index: 6554335 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0260. Min Range: -8.0260
Max Act: 7.2447. Min Act: -0.1700
Data Index: 2348989 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0260. Min Range: -8.0260
Max Act: 7.1197. Min Act: -0.1700
Data Index: 843438 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0260. Min Range: -8.0260
Max Act: 7.0885. Min Act: -0.1700
Data Index: 3172314 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0260. Min Range: -8.0260
Max Act: 6.9322. Min Act: -0.1700
Data Index: 448265 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0260. Min Range: -8.0260
Max Act: 6.9010. Min Act: -0.1700
Data Index: 7436336 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0260. Min Range: -8.0260
Max Act: 6.8385. Min Act: -0.1700
Data Index: 712112 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0260. Min Range: -8.0260
Max Act: 6.8385. Min Act: -0.1700
Data Index: 7906550 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0260. Min Range: -8.0260
Max Act: 6.8385. Min Act: -0.1700
Data Index: 843439 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0260. Min Range: -8.0260
Max Act: 6.7760. Min Act: -0.1700
Data Index: 7912122 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0260. Min Range: -8.0260
Max Act: 6.7760. Min Act: -0.1700
Data Index: 5954072 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0260. Min Range: -8.0260
Max Act: 6.7760. Min Act: -0.1700
Data Index: 1521650 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0260. Min Range: -8.0260
Max Act: 6.7760. Min Act: -0.1700
Data Index: 6487148 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0260. Min Range: -8.0260
Max Act: 6.7447. Min Act: -0.1700
Data Index: 8007542 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0260. Min Range: -8.0260
Max Act: 6.7447. Min Act: -0.1700
Data Index: 232996 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0260. Min Range: -8.0260
Max Act: 6.7135. Min Act: -0.1700
Data Index: 8151677 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0260. Min Range: -8.0260
Max Act: 6.7447. Min Act: -0.1700
Data Index: 2191415 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19