Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2378 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4345. Min Range: -8.4345
Max Act: 8.4345. Min Act: -0.1700
Data Index: 5263663 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4345. Min Range: -8.4345
Max Act: 8.2470. Min Act: -0.1700
Data Index: 7904583 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4345. Min Range: -8.4345
Max Act: 8.1845. Min Act: -0.1700
Data Index: 5650857 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4345. Min Range: -8.4345
Max Act: 8.1845. Min Act: -0.1700
Data Index: 1432354 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4345. Min Range: -8.4345
Max Act: 8.0907. Min Act: -0.1700
Data Index: 8289418 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4345. Min Range: -8.4345
Max Act: 8.0907. Min Act: -0.1700
Data Index: 2866230 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4345. Min Range: -8.4345
Max Act: 8.0907. Min Act: -0.1700
Data Index: 2437011 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4345. Min Range: -8.4345
Max Act: 8.0907. Min Act: -0.1700
Data Index: 2832660 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4345. Min Range: -8.4345
Max Act: 7.9970. Min Act: -0.1700
Data Index: 2063797 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4345. Min Range: -8.4345
Max Act: 7.9970. Min Act: -0.1700
Data Index: 6777827 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4345. Min Range: -8.4345
Max Act: 7.9345. Min Act: -0.1700
Data Index: 4776357 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4345. Min Range: -8.4345
Max Act: 7.9345. Min Act: -0.1700
Data Index: 6575888 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4345. Min Range: -8.4345
Max Act: 7.9345. Min Act: -0.1700
Data Index: 3662725 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4345. Min Range: -8.4345
Max Act: 7.9657. Min Act: -0.1700
Data Index: 7500255 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4345. Min Range: -8.4345
Max Act: 7.8407. Min Act: -0.1700
Data Index: 1026598 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4345. Min Range: -8.4345
Max Act: 7.9032. Min Act: -0.1700
Data Index: 8276685 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4345. Min Range: -8.4345
Max Act: 7.8720. Min Act: -0.1700
Data Index: 2757220 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4345. Min Range: -8.4345
Max Act: 7.8720. Min Act: -0.1700
Data Index: 5652288 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4345. Min Range: -8.4345
Max Act: 7.8407. Min Act: -0.1700
Data Index: 821635 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4345. Min Range: -8.4345
Max Act: 7.8720. Min Act: -0.1700
Data Index: 4355888 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19