Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4641 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7612. Min Range: -7.7612
Max Act: 7.7612. Min Act: -0.1700
Data Index: 5475973 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7612. Min Range: -7.7612
Max Act: 7.5737. Min Act: -0.1700
Data Index: 3172608 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7612. Min Range: -7.7612
Max Act: 7.4487. Min Act: -0.1700
Data Index: 4362841 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7612. Min Range: -7.7612
Max Act: 7.2612. Min Act: -0.1700
Data Index: 1376396 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7612. Min Range: -7.7612
Max Act: 7.2300. Min Act: -0.1700
Data Index: 4037907 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7612. Min Range: -7.7612
Max Act: 7.1362. Min Act: -0.1700
Data Index: 6914387 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7612. Min Range: -7.7612
Max Act: 7.1675. Min Act: -0.1700
Data Index: 7010762 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7612. Min Range: -7.7612
Max Act: 7.0737. Min Act: -0.1700
Data Index: 3683301 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7612. Min Range: -7.7612
Max Act: 7.1050. Min Act: -0.1700
Data Index: 6252468 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7612. Min Range: -7.7612
Max Act: 7.0737. Min Act: -0.1700
Data Index: 4202808 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7612. Min Range: -7.7612
Max Act: 7.0112. Min Act: -0.1700
Data Index: 6012730 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7612. Min Range: -7.7612
Max Act: 6.9800. Min Act: -0.1700
Data Index: 6486652 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7612. Min Range: -7.7612
Max Act: 6.9800. Min Act: -0.1700
Data Index: 2453911 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7612. Min Range: -7.7612
Max Act: 6.9800. Min Act: -0.1700
Data Index: 3321023 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7612. Min Range: -7.7612
Max Act: 6.8550. Min Act: -0.1700
Data Index: 1333687 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7612. Min Range: -7.7612
Max Act: 6.8862. Min Act: -0.1700
Data Index: 6249438 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7612. Min Range: -7.7612
Max Act: 6.8862. Min Act: -0.1700
Data Index: 8545725 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7612. Min Range: -7.7612
Max Act: 6.8550. Min Act: -0.1700
Data Index: 7747175 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7612. Min Range: -7.7612
Max Act: 6.8550. Min Act: -0.1700
Data Index: 5915528 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7612. Min Range: -7.7612
Max Act: 6.7612. Min Act: -0.1700
Data Index: 6098374 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19