Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1614 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0002. Min Range: -5.0002
Max Act: 5.0002. Min Act: -0.1700
Data Index: 7775649 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.8127. Min Act: -0.1700
Data Index: 5519047 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.8127. Min Act: -0.1700
Data Index: 2107176 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.8439. Min Act: -0.1700
Data Index: 4533621 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.7814. Min Act: -0.1700
Data Index: 8262130 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.7502. Min Act: -0.1700
Data Index: 5519051 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.7502. Min Act: -0.1700
Data Index: 5519049 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.7502. Min Act: -0.1700
Data Index: 2926522 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.7189. Min Act: -0.1700
Data Index: 6783565 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.7189. Min Act: -0.1700
Data Index: 5519046 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.6877. Min Act: -0.1700
Data Index: 4695250 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.6564. Min Act: -0.1700
Data Index: 2192071 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.6564. Min Act: -0.1700
Data Index: 7474003 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.6564. Min Act: -0.1700
Data Index: 5438139 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.6252. Min Act: -0.1700
Data Index: 2937368 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.6252. Min Act: -0.1700
Data Index: 6472424 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.5939. Min Act: -0.1700
Data Index: 8760193 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.6252. Min Act: -0.1700
Data Index: 4383482 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.5939. Min Act: -0.1700
Data Index: 3462899 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0002. Min Range: -5.0002
Max Act: 4.5939. Min Act: -0.1700
Data Index: 7735037 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19