Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4479 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.2755. Min Act: -0.1700
Data Index: 1106982 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.2442. Min Act: -0.1700
Data Index: 384559 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.2130. Min Act: -0.1700
Data Index: 2504274 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.1817. Min Act: -0.1700
Data Index: 7676528 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.1817. Min Act: -0.1700
Data Index: 6264845 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.1505. Min Act: -0.1700
Data Index: 7535813 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.2130. Min Act: -0.1700
Data Index: 6855324 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.1505. Min Act: -0.1700
Data Index: 5459466 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.1192. Min Act: -0.1700
Data Index: 3884583 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.1505. Min Act: -0.1700
Data Index: 7453740 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.1505. Min Act: -0.1700
Data Index: 8434822 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.1192. Min Act: -0.1700
Data Index: 3338585 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.0880. Min Act: -0.1700
Data Index: 2347246 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.0567. Min Act: -0.1700
Data Index: 1106997 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.0567. Min Act: -0.1700
Data Index: 1106964 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2755. Min Range: -6.2755
Max Act: 6.0255. Min Act: -0.1700
Data Index: 5336557 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2755. Min Range: -6.2755
Max Act: 5.9942. Min Act: -0.1700
Data Index: 7260644 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2755. Min Range: -6.2755
Max Act: 5.9942. Min Act: -0.1700
Data Index: 8765345 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2755. Min Range: -6.2755
Max Act: 5.9317. Min Act: -0.1700
Data Index: 4366622 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2755. Min Range: -6.2755
Max Act: 5.9005. Min Act: -0.1700
Data Index: 607563 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19