Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2805 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.3103. Min Act: -0.1700
Data Index: 6818491 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.2478. Min Act: -0.1700
Data Index: 3235117 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.2165. Min Act: -0.1700
Data Index: 8676883 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.1852. Min Act: -0.1700
Data Index: 3244138 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.1227. Min Act: -0.1700
Data Index: 1343941 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.0915. Min Act: -0.1700
Data Index: 6861848 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.0915. Min Act: -0.1700
Data Index: 5050523 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.0915. Min Act: -0.1700
Data Index: 2121853 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.0602. Min Act: -0.1700
Data Index: 6543547 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.0602. Min Act: -0.1700
Data Index: 6903655 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.0915. Min Act: -0.1700
Data Index: 4876379 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.0290. Min Act: -0.1700
Data Index: 3031934 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.0290. Min Act: -0.1700
Data Index: 5538508 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.0602. Min Act: -0.1700
Data Index: 3146168 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.0290. Min Act: -0.1700
Data Index: 781381 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.9977. Min Act: -0.1700
Data Index: 4532192 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.9977. Min Act: -0.1700
Data Index: 2069697 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.0290. Min Act: -0.1700
Data Index: 2050294 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.9977. Min Act: -0.1700
Data Index: 6250024 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.9664. Min Act: -0.1700
Data Index: 3914158 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19