Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4811 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4421. Min Range: -6.4421
Max Act: 6.4421. Min Act: -0.1700
Data Index: 5349487 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4421. Min Range: -6.4421
Max Act: 6.2546. Min Act: -0.1700
Data Index: 6399606 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4421. Min Range: -6.4421
Max Act: 6.1609. Min Act: -0.1700
Data Index: 4652857 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.9734. Min Act: -0.1700
Data Index: 1525731 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.8796. Min Act: -0.1700
Data Index: 2829685 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.9109. Min Act: -0.1700
Data Index: 5152088 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.7234. Min Act: -0.1700
Data Index: 4042657 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.7234. Min Act: -0.1700
Data Index: 4588437 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.6921. Min Act: -0.1700
Data Index: 1187881 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.7234. Min Act: -0.1700
Data Index: 1088772 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.6609. Min Act: -0.1700
Data Index: 3436210 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.6296. Min Act: -0.1700
Data Index: 7119414 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.6296. Min Act: -0.1700
Data Index: 4576286 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.6296. Min Act: -0.1700
Data Index: 103263 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.6296. Min Act: -0.1700
Data Index: 2580795 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.6296. Min Act: -0.1700
Data Index: 2695147 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.5984. Min Act: -0.1700
Data Index: 1789650 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.5984. Min Act: -0.1700
Data Index: 6900294 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.5671. Min Act: -0.1700
Data Index: 508660 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4421. Min Range: -6.4421
Max Act: 5.5671. Min Act: -0.1700
Data Index: 150288 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19