Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4425 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1633. Min Range: -6.1633
Max Act: 6.1633. Min Act: -0.1700
Data Index: 6712474 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1633. Min Range: -6.1633
Max Act: 6.0383. Min Act: -0.1700
Data Index: 7867526 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1633. Min Range: -6.1633
Max Act: 6.0383. Min Act: -0.1700
Data Index: 3220346 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.9445. Min Act: -0.1700
Data Index: 675634 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.9133. Min Act: -0.1700
Data Index: 6999126 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.9445. Min Act: -0.1700
Data Index: 2293681 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.9133. Min Act: -0.1700
Data Index: 6500850 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.8820. Min Act: -0.1700
Data Index: 2769136 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.8820. Min Act: -0.1700
Data Index: 3942831 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.8820. Min Act: -0.1700
Data Index: 3447623 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.8508. Min Act: -0.1700
Data Index: 8562603 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.8820. Min Act: -0.1700
Data Index: 8078176 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.8508. Min Act: -0.1700
Data Index: 6369467 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.8508. Min Act: -0.1700
Data Index: 7547979 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.8195. Min Act: -0.1700
Data Index: 1316318 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.8195. Min Act: -0.1700
Data Index: 557893 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.8508. Min Act: -0.1700
Data Index: 3791938 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.8195. Min Act: -0.1700
Data Index: 5374654 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.7883. Min Act: -0.1700
Data Index: 6428988 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1633. Min Range: -6.1633
Max Act: 5.7883. Min Act: -0.1700
Data Index: 2481785 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19