Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4631 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5600. Min Range: -9.5600
Max Act: 9.5600. Min Act: -0.1700
Data Index: 1352898 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5600. Min Range: -9.5600
Max Act: 9.4350. Min Act: -0.1700
Data Index: 3271650 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5600. Min Range: -9.5600
Max Act: 9.4350. Min Act: -0.1700
Data Index: 6794113 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5600. Min Range: -9.5600
Max Act: 9.3100. Min Act: -0.1700
Data Index: 4334849 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5600. Min Range: -9.5600
Max Act: 9.1225. Min Act: -0.1700
Data Index: 3634473 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5600. Min Range: -9.5600
Max Act: 9.1850. Min Act: -0.1700
Data Index: 1555800 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5600. Min Range: -9.5600
Max Act: 9.1225. Min Act: -0.1700
Data Index: 8083365 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5600. Min Range: -9.5600
Max Act: 9.1225. Min Act: -0.1700
Data Index: 8719469 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5600. Min Range: -9.5600
Max Act: 9.0600. Min Act: -0.1700
Data Index: 7410703 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5600. Min Range: -9.5600
Max Act: 9.1225. Min Act: -0.1700
Data Index: 1881929 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5600. Min Range: -9.5600
Max Act: 9.0600. Min Act: -0.1700
Data Index: 5633332 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5600. Min Range: -9.5600
Max Act: 8.9975. Min Act: -0.1700
Data Index: 5646788 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5600. Min Range: -9.5600
Max Act: 8.9975. Min Act: -0.1700
Data Index: 3898792 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5600. Min Range: -9.5600
Max Act: 8.9350. Min Act: -0.1700
Data Index: 84054 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5600. Min Range: -9.5600
Max Act: 8.9350. Min Act: -0.1700
Data Index: 6033376 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5600. Min Range: -9.5600
Max Act: 8.9350. Min Act: -0.1700
Data Index: 8428286 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5600. Min Range: -9.5600
Max Act: 8.9350. Min Act: -0.1700
Data Index: 1148246 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5600. Min Range: -9.5600
Max Act: 8.9975. Min Act: -0.1700
Data Index: 3950079 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5600. Min Range: -9.5600
Max Act: 8.9350. Min Act: -0.1700
Data Index: 3276412 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5600. Min Range: -9.5600
Max Act: 8.8725. Min Act: -0.1700
Data Index: 3253788 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19