Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 870 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1140. Min Range: -5.1140
Max Act: 5.1140. Min Act: -0.1700
Data Index: 3566286 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1140. Min Range: -5.1140
Max Act: 5.0203. Min Act: -0.1700
Data Index: 7087888 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.9890. Min Act: -0.1700
Data Index: 6315738 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1140. Min Range: -5.1140
Max Act: 5.0203. Min Act: -0.1700
Data Index: 5667527 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.9578. Min Act: -0.1700
Data Index: 3067356 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.9578. Min Act: -0.1700
Data Index: 812563 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.8640. Min Act: -0.1700
Data Index: 8105238 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.8953. Min Act: -0.1700
Data Index: 4017309 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.8015. Min Act: -0.1700
Data Index: 7073699 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.8015. Min Act: -0.1700
Data Index: 6315737 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.8015. Min Act: -0.1700
Data Index: 7468590 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.8015. Min Act: -0.1700
Data Index: 3230096 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.8328. Min Act: -0.1700
Data Index: 3524677 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.8015. Min Act: -0.1700
Data Index: 6829059 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.7703. Min Act: -0.1700
Data Index: 623528 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.7703. Min Act: -0.1700
Data Index: 6645467 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.7703. Min Act: -0.1700
Data Index: 8565625 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.7390. Min Act: -0.1700
Data Index: 6493440 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.7390. Min Act: -0.1700
Data Index: 225615 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1140. Min Range: -5.1140
Max Act: 4.7390. Min Act: -0.1700
Data Index: 7004395 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19