Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4884 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1786. Min Range: -8.1786
Max Act: 8.1786. Min Act: -0.1700
Data Index: 1063816 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.9911. Min Act: -0.1700
Data Index: 5983497 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.8036. Min Act: -0.1700
Data Index: 7582389 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.7411. Min Act: -0.1700
Data Index: 568814 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.7098. Min Act: -0.1700
Data Index: 7872749 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.7098. Min Act: -0.1700
Data Index: 7903284 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.7098. Min Act: -0.1700
Data Index: 974464 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.6473. Min Act: -0.1700
Data Index: 7614937 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.6161. Min Act: -0.1700
Data Index: 6226305 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.6161. Min Act: -0.1700
Data Index: 4728106 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.5848. Min Act: -0.1700
Data Index: 110776 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.6473. Min Act: -0.1700
Data Index: 5024500 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.6161. Min Act: -0.1700
Data Index: 7213024 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.5848. Min Act: -0.1700
Data Index: 6028144 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.5848. Min Act: -0.1700
Data Index: 2197702 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.5848. Min Act: -0.1700
Data Index: 3420313 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.5848. Min Act: -0.1700
Data Index: 4504289 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.5536. Min Act: -0.1700
Data Index: 4414625 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.5536. Min Act: -0.1700
Data Index: 1164519 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1786. Min Range: -8.1786
Max Act: 7.5848. Min Act: -0.1700
Data Index: 3439016 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19