Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2888 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.8531. Min Act: -0.1700
Data Index: 4740193 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.6656. Min Act: -0.1700
Data Index: 7676737 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.6656. Min Act: -0.1700
Data Index: 5165089 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.6031. Min Act: -0.1700
Data Index: 2774328 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.5406. Min Act: -0.1700
Data Index: 1838576 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.5094. Min Act: -0.1700
Data Index: 6252250 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.4156. Min Act: -0.1700
Data Index: 8587535 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.4156. Min Act: -0.1700
Data Index: 3799621 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.3531. Min Act: -0.1700
Data Index: 8310654 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.2906. Min Act: -0.1700
Data Index: 788392 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.2594. Min Act: -0.1700
Data Index: 8424533 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.2906. Min Act: -0.1700
Data Index: 2900053 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.2906. Min Act: -0.1700
Data Index: 7760545 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.3219. Min Act: -0.1700
Data Index: 8310350 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.2594. Min Act: -0.1700
Data Index: 2261099 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.2594. Min Act: -0.1700
Data Index: 2801521 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.2594. Min Act: -0.1700
Data Index: 2955151 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.2594. Min Act: -0.1700
Data Index: 7837896 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.2281. Min Act: -0.1700
Data Index: 1841431 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8531. Min Range: -7.8531
Max Act: 7.2281. Min Act: -0.1700
Data Index: 5204917 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19