Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3885 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.5679. Min Act: -0.1700
Data Index: 2831966 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.4429. Min Act: -0.1700
Data Index: 8320016 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.4429. Min Act: -0.1700
Data Index: 772858 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.3491. Min Act: -0.1700
Data Index: 241421 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.3804. Min Act: -0.1700
Data Index: 5220226 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.3491. Min Act: -0.1700
Data Index: 3769302 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.3179. Min Act: -0.1700
Data Index: 2800936 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.2866. Min Act: -0.1700
Data Index: 7762248 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.2866. Min Act: -0.1700
Data Index: 7290946 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.2554. Min Act: -0.1700
Data Index: 7435760 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.2554. Min Act: -0.1700
Data Index: 7999741 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.2554. Min Act: -0.1700
Data Index: 8283851 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.2554. Min Act: -0.1700
Data Index: 4591493 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.2554. Min Act: -0.1700
Data Index: 4991978 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.2241. Min Act: -0.1700
Data Index: 1827879 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.2241. Min Act: -0.1700
Data Index: 4355496 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.2241. Min Act: -0.1700
Data Index: 2557901 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.1929. Min Act: -0.1700
Data Index: 2231062 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.1929. Min Act: -0.1700
Data Index: 4180331 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5679. Min Range: -5.5679
Max Act: 5.1929. Min Act: -0.1700
Data Index: 3065102 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19