Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 622 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.9164. Min Act: -0.1700
Data Index: 1636316 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.9164. Min Act: -0.1700
Data Index: 5521029 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.8227. Min Act: -0.1700
Data Index: 8062022 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.8227. Min Act: -0.1700
Data Index: 1187120 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.8227. Min Act: -0.1700
Data Index: 7977162 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.8227. Min Act: -0.1700
Data Index: 4515637 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.8227. Min Act: -0.1700
Data Index: 2084595 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.7914. Min Act: -0.1700
Data Index: 3455963 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.7914. Min Act: -0.1700
Data Index: 686256 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.7914. Min Act: -0.1700
Data Index: 3329168 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.7914. Min Act: -0.1700
Data Index: 2084597 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.7914. Min Act: -0.1700
Data Index: 2783232 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.7914. Min Act: -0.1700
Data Index: 2700572 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.7602. Min Act: -0.1700
Data Index: 6951851 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.7602. Min Act: -0.1700
Data Index: 6677128 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.7914. Min Act: -0.1700
Data Index: 643486 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.7602. Min Act: -0.1700
Data Index: 328498 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.7602. Min Act: -0.1700
Data Index: 5919676 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.7602. Min Act: -0.1700
Data Index: 4052504 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9164. Min Range: -5.9164
Max Act: 5.7289. Min Act: -0.1700
Data Index: 5492872 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19