Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2285 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.6549. Min Act: -0.1700
Data Index: 4526379 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.5924. Min Act: -0.1700
Data Index: 2582634 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.5611. Min Act: -0.1700
Data Index: 7663691 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4986. Min Act: -0.1700
Data Index: 2368289 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4674. Min Act: -0.1700
Data Index: 6446223 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4674. Min Act: -0.1700
Data Index: 413974 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4674. Min Act: -0.1700
Data Index: 5212213 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4674. Min Act: -0.1700
Data Index: 2026475 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4674. Min Act: -0.1700
Data Index: 7283592 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4674. Min Act: -0.1700
Data Index: 6273241 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4674. Min Act: -0.1700
Data Index: 2853710 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4361. Min Act: -0.1700
Data Index: 8161910 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4361. Min Act: -0.1700
Data Index: 5087126 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4361. Min Act: -0.1700
Data Index: 6649437 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4361. Min Act: -0.1700
Data Index: 7002494 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4361. Min Act: -0.1700
Data Index: 2794397 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4049. Min Act: -0.1700
Data Index: 3325666 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4049. Min Act: -0.1700
Data Index: 724646 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.3736. Min Act: -0.1700
Data Index: 5246352 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4049. Min Act: -0.1700
Data Index: 1624275 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19