Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1091 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.4917. Min Act: -0.1700
Data Index: 7640037 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.3980. Min Act: -0.1700
Data Index: 1983788 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.2730. Min Act: -0.1700
Data Index: 1103056 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.2730. Min Act: -0.1700
Data Index: 6516123 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.2417. Min Act: -0.1700
Data Index: 7407481 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.2105. Min Act: -0.1700
Data Index: 5975265 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.2417. Min Act: -0.1700
Data Index: 6135130 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.1792. Min Act: -0.1700
Data Index: 5329351 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.1792. Min Act: -0.1700
Data Index: 8443902 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.1167. Min Act: -0.1700
Data Index: 4834766 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.1480. Min Act: -0.1700
Data Index: 5416653 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.1167. Min Act: -0.1700
Data Index: 4557356 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.1480. Min Act: -0.1700
Data Index: 7193197 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.1480. Min Act: -0.1700
Data Index: 2598446 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.1167. Min Act: -0.1700
Data Index: 2136932 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.1167. Min Act: -0.1700
Data Index: 2549577 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.1167. Min Act: -0.1700
Data Index: 2163930 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.1167. Min Act: -0.1700
Data Index: 6007047 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.1480. Min Act: -0.1700
Data Index: 3725372 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4917. Min Range: -4.4917
Max Act: 4.1167. Min Act: -0.1700
Data Index: 8177427 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19