Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5595 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1350. Min Range: -5.1350
Max Act: 5.1350. Min Act: -0.1700
Data Index: 7962773 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1350. Min Range: -5.1350
Max Act: 5.1350. Min Act: -0.1700
Data Index: 3607375 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1350. Min Range: -5.1350
Max Act: 5.0725. Min Act: -0.1700
Data Index: 8220116 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1350. Min Range: -5.1350
Max Act: 5.0412. Min Act: -0.1700
Data Index: 692162 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1350. Min Range: -5.1350
Max Act: 5.0412. Min Act: -0.1700
Data Index: 8154796 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1350. Min Range: -5.1350
Max Act: 4.9787. Min Act: -0.1700
Data Index: 5271903 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1350. Min Range: -5.1350
Max Act: 5.0100. Min Act: -0.1700
Data Index: 251769 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1350. Min Range: -5.1350
Max Act: 4.9475. Min Act: -0.1700
Data Index: 7965055 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1350. Min Range: -5.1350
Max Act: 4.9787. Min Act: -0.1700
Data Index: 387365 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1350. Min Range: -5.1350
Max Act: 4.9787. Min Act: -0.1700
Data Index: 8371931 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1350. Min Range: -5.1350
Max Act: 4.9787. Min Act: -0.1700
Data Index: 4763561 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1350. Min Range: -5.1350
Max Act: 5.0100. Min Act: -0.1700
Data Index: 99239 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1350. Min Range: -5.1350
Max Act: 4.9787. Min Act: -0.1700
Data Index: 6904430 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1350. Min Range: -5.1350
Max Act: 4.9787. Min Act: -0.1700
Data Index: 5362524 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1350. Min Range: -5.1350
Max Act: 4.9787. Min Act: -0.1700
Data Index: 8424864 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1350. Min Range: -5.1350
Max Act: 4.9787. Min Act: -0.1700
Data Index: 3679851 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1350. Min Range: -5.1350
Max Act: 4.9475. Min Act: -0.1700
Data Index: 4229360 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1350. Min Range: -5.1350
Max Act: 4.9475. Min Act: -0.1700
Data Index: 3627836 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1350. Min Range: -5.1350
Max Act: 4.9475. Min Act: -0.1700
Data Index: 20163 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1350. Min Range: -5.1350
Max Act: 4.9162. Min Act: -0.1700
Data Index: 1418556 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19