Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2389. Min Range: -6.2389
Max Act: 6.2389. Min Act: -0.1700
Data Index: 6641971 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2389. Min Range: -6.2389
Max Act: 6.1452. Min Act: -0.1700
Data Index: 3053279 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2389. Min Range: -6.2389
Max Act: 6.1452. Min Act: -0.1700
Data Index: 2498706 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.9577. Min Act: -0.1700
Data Index: 460352 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.9264. Min Act: -0.1700
Data Index: 4935835 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.8952. Min Act: -0.1700
Data Index: 4249616 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.8639. Min Act: -0.1700
Data Index: 1081634 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.7702. Min Act: -0.1700
Data Index: 8751555 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.7389. Min Act: -0.1700
Data Index: 8259032 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.7389. Min Act: -0.1700
Data Index: 3012490 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.7077. Min Act: -0.1700
Data Index: 819508 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.6452. Min Act: -0.1700
Data Index: 7689372 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.5827. Min Act: -0.1700
Data Index: 7930250 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.5514. Min Act: -0.1700
Data Index: 950093 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.5514. Min Act: -0.1700
Data Index: 1468649 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.5827. Min Act: -0.1700
Data Index: 3872559 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.5202. Min Act: -0.1700
Data Index: 5730709 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.4889. Min Act: -0.1700
Data Index: 2592598 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.4889. Min Act: -0.1700
Data Index: 2521312 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.5202. Min Act: -0.1700
Data Index: 2334277 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19