Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1258 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.9890. Min Act: -0.1700
Data Index: 8056154 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.8015. Min Act: -0.1700
Data Index: 2930630 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.6140. Min Act: -0.1700
Data Index: 5019398 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.4265. Min Act: -0.1700
Data Index: 1669621 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.4265. Min Act: -0.1700
Data Index: 7111917 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.3640. Min Act: -0.1700
Data Index: 2412893 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.2390. Min Act: -0.1700
Data Index: 3023650 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.2390. Min Act: -0.1700
Data Index: 1149934 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.1765. Min Act: -0.1700
Data Index: 444876 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.1765. Min Act: -0.1700
Data Index: 351948 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.1140. Min Act: -0.1700
Data Index: 4453069 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.1765. Min Act: -0.1700
Data Index: 4875190 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.1140. Min Act: -0.1700
Data Index: 5663372 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.1140. Min Act: -0.1700
Data Index: 35092 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.1140. Min Act: -0.1700
Data Index: 3667055 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.1140. Min Act: -0.1700
Data Index: 6157664 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.1140. Min Act: -0.1700
Data Index: 6602148 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.1140. Min Act: -0.1700
Data Index: 4381982 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.1140. Min Act: -0.1700
Data Index: 1599441 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9890. Min Range: -8.9890
Max Act: 8.0515. Min Act: -0.1700
Data Index: 3151139 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19