Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3313 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7008. Min Range: -7.7008
Max Act: 7.7008. Min Act: -0.1700
Data Index: 900909 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7008. Min Range: -7.7008
Max Act: 7.4508. Min Act: -0.1700
Data Index: 7721852 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7008. Min Range: -7.7008
Max Act: 7.2945. Min Act: -0.1700
Data Index: 3870040 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7008. Min Range: -7.7008
Max Act: 7.2320. Min Act: -0.1700
Data Index: 4610664 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7008. Min Range: -7.7008
Max Act: 7.2320. Min Act: -0.1700
Data Index: 133075 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7008. Min Range: -7.7008
Max Act: 7.2008. Min Act: -0.1700
Data Index: 4991630 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7008. Min Range: -7.7008
Max Act: 7.1070. Min Act: -0.1700
Data Index: 7700188 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7008. Min Range: -7.7008
Max Act: 7.1070. Min Act: -0.1700
Data Index: 3492271 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7008. Min Range: -7.7008
Max Act: 7.0445. Min Act: -0.1700
Data Index: 3139123 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7008. Min Range: -7.7008
Max Act: 6.9820. Min Act: -0.1700
Data Index: 2888879 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7008. Min Range: -7.7008
Max Act: 6.9820. Min Act: -0.1700
Data Index: 6634717 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7008. Min Range: -7.7008
Max Act: 6.9195. Min Act: -0.1700
Data Index: 643854 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7008. Min Range: -7.7008
Max Act: 6.8570. Min Act: -0.1700
Data Index: 8294396 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7008. Min Range: -7.7008
Max Act: 6.7945. Min Act: -0.1700
Data Index: 4165324 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7008. Min Range: -7.7008
Max Act: 6.7945. Min Act: -0.1700
Data Index: 2662365 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7008. Min Range: -7.7008
Max Act: 6.7945. Min Act: -0.1700
Data Index: 587930 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7008. Min Range: -7.7008
Max Act: 6.7633. Min Act: -0.1700
Data Index: 7945309 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7008. Min Range: -7.7008
Max Act: 6.7320. Min Act: -0.1700
Data Index: 5110192 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7008. Min Range: -7.7008
Max Act: 6.7320. Min Act: -0.1700
Data Index: 6263197 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7008. Min Range: -7.7008
Max Act: 6.7320. Min Act: -0.1700
Data Index: 1621788 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19