Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5097 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3073. Min Range: -5.3073
Max Act: 5.3073. Min Act: -0.1700
Data Index: 4105119 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3073. Min Range: -5.3073
Max Act: 5.0885. Min Act: -0.1700
Data Index: 506391 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3073. Min Range: -5.3073
Max Act: 5.0260. Min Act: -0.1700
Data Index: 7882622 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.9948. Min Act: -0.1700
Data Index: 6224567 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8698. Min Act: -0.1700
Data Index: 8194892 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8698. Min Act: -0.1700
Data Index: 1179783 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8698. Min Act: -0.1700
Data Index: 4743974 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8698. Min Act: -0.1700
Data Index: 4691049 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8698. Min Act: -0.1700
Data Index: 1152640 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8385. Min Act: -0.1700
Data Index: 1519305 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8385. Min Act: -0.1700
Data Index: 3685570 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8385. Min Act: -0.1700
Data Index: 2153572 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8385. Min Act: -0.1700
Data Index: 770065 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8073. Min Act: -0.1700
Data Index: 2973071 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8385. Min Act: -0.1700
Data Index: 8511296 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8073. Min Act: -0.1700
Data Index: 6412890 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8385. Min Act: -0.1700
Data Index: 5931535 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8073. Min Act: -0.1700
Data Index: 7029122 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.8073. Min Act: -0.1700
Data Index: 4238117 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3073. Min Range: -5.3073
Max Act: 4.7760. Min Act: -0.1700
Data Index: 5911854 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19