Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3215 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0630. Min Range: -5.0630
Max Act: 5.0630. Min Act: -0.1700
Data Index: 2524490 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0630. Min Range: -5.0630
Max Act: 5.0317. Min Act: -0.1700
Data Index: 4516661 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0630. Min Range: -5.0630
Max Act: 5.0317. Min Act: -0.1700
Data Index: 2012794 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0630. Min Range: -5.0630
Max Act: 5.0317. Min Act: -0.1700
Data Index: 5301960 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.9380. Min Act: -0.1700
Data Index: 7111648 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.9380. Min Act: -0.1700
Data Index: 108159 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.9067. Min Act: -0.1700
Data Index: 2584954 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.9067. Min Act: -0.1700
Data Index: 5435058 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.9067. Min Act: -0.1700
Data Index: 5094541 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.9067. Min Act: -0.1700
Data Index: 4871156 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.8755. Min Act: -0.1700
Data Index: 2739354 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.8442. Min Act: -0.1700
Data Index: 949980 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.8442. Min Act: -0.1700
Data Index: 8138862 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.7817. Min Act: -0.1700
Data Index: 6734839 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.7817. Min Act: -0.1700
Data Index: 4887271 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.8130. Min Act: -0.1700
Data Index: 5452311 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.7817. Min Act: -0.1700
Data Index: 826409 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.7817. Min Act: -0.1700
Data Index: 1732622 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.7505. Min Act: -0.1700
Data Index: 5385809 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0630. Min Range: -5.0630
Max Act: 4.7817. Min Act: -0.1700
Data Index: 2549317 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19