Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1675. Min Range: -6.1675
Max Act: 6.1675. Min Act: -0.1700
Data Index: 5358185 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.9487. Min Act: -0.1700
Data Index: 5995802 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.8550. Min Act: -0.1700
Data Index: 4866189 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.7925. Min Act: -0.1700
Data Index: 8568880 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.7612. Min Act: -0.1700
Data Index: 1748379 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.7612. Min Act: -0.1700
Data Index: 4145626 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.7300. Min Act: -0.1700
Data Index: 3061139 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.7300. Min Act: -0.1700
Data Index: 7252130 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.6987. Min Act: -0.1700
Data Index: 7707680 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.6050. Min Act: -0.1700
Data Index: 3577582 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.5737. Min Act: -0.1700
Data Index: 5883094 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.5737. Min Act: -0.1700
Data Index: 846327 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.5737. Min Act: -0.1700
Data Index: 1736732 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.5425. Min Act: -0.1700
Data Index: 1803383 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.5737. Min Act: -0.1700
Data Index: 2234018 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.5737. Min Act: -0.1700
Data Index: 745695 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.5425. Min Act: -0.1700
Data Index: 5864381 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.5112. Min Act: -0.1700
Data Index: 5281118 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.4800. Min Act: -0.1700
Data Index: 8653656 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1675. Min Range: -6.1675
Max Act: 5.4800. Min Act: -0.1700
Data Index: 474604 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19