Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3043 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2310. Min Range: -4.2310
Max Act: 4.2310. Min Act: -0.1700
Data Index: 5331288 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2310. Min Range: -4.2310
Max Act: 4.1372. Min Act: -0.1700
Data Index: 8817296 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2310. Min Range: -4.2310
Max Act: 4.1060. Min Act: -0.1700
Data Index: 3746480 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2310. Min Range: -4.2310
Max Act: 4.1060. Min Act: -0.1700
Data Index: 4245881 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2310. Min Range: -4.2310
Max Act: 4.0747. Min Act: -0.1700
Data Index: 4021225 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.9809. Min Act: -0.1700
Data Index: 8313638 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.9809. Min Act: -0.1700
Data Index: 4734766 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.9809. Min Act: -0.1700
Data Index: 784557 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.9184. Min Act: -0.1700
Data Index: 3667895 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.9497. Min Act: -0.1700
Data Index: 6953178 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.9184. Min Act: -0.1700
Data Index: 883984 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.9497. Min Act: -0.1700
Data Index: 5948104 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.9184. Min Act: -0.1700
Data Index: 6360483 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.9184. Min Act: -0.1700
Data Index: 3050489 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.9184. Min Act: -0.1700
Data Index: 2252922 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.8871. Min Act: -0.1700
Data Index: 912857 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.8871. Min Act: -0.1700
Data Index: 5384788 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.8559. Min Act: -0.1700
Data Index: 2842841 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.8559. Min Act: -0.1700
Data Index: 4690701 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2310. Min Range: -4.2310
Max Act: 3.8559. Min Act: -0.1700
Data Index: 109802 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19