Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4812 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.9651. Min Act: -0.1700
Data Index: 3384323 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.7151. Min Act: -0.1700
Data Index: 1077982 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.7151. Min Act: -0.1700
Data Index: 4879493 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.4651. Min Act: -0.1700
Data Index: 8740990 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.3401. Min Act: -0.1700
Data Index: 6554757 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.2776. Min Act: -0.1700
Data Index: 5484069 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.2151. Min Act: -0.1700
Data Index: 1137766 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.2151. Min Act: -0.1700
Data Index: 6477170 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.1526. Min Act: -0.1700
Data Index: 7127656 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.0901. Min Act: -0.1700
Data Index: 4594870 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.0901. Min Act: -0.1700
Data Index: 6467632 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.0276. Min Act: -0.1700
Data Index: 2795422 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.0276. Min Act: -0.1700
Data Index: 5113573 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9651. Min Range: -9.9651
Max Act: 9.0276. Min Act: -0.1700
Data Index: 4688070 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9651. Min Range: -9.9651
Max Act: 8.9651. Min Act: -0.1700
Data Index: 2093901 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9651. Min Range: -9.9651
Max Act: 8.9026. Min Act: -0.1700
Data Index: 1346369 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9651. Min Range: -9.9651
Max Act: 8.9651. Min Act: -0.1700
Data Index: 7142110 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9651. Min Range: -9.9651
Max Act: 8.9026. Min Act: -0.1700
Data Index: 6413194 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9651. Min Range: -9.9651
Max Act: 8.9026. Min Act: -0.1700
Data Index: 5974822 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9651. Min Range: -9.9651
Max Act: 8.9026. Min Act: -0.1700
Data Index: 6900342 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19