Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1088 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8739. Min Range: -8.8739
Max Act: 8.8739. Min Act: -0.1700
Data Index: 2933545 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8739. Min Range: -8.8739
Max Act: 8.3739. Min Act: -0.1700
Data Index: 2846212 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8739. Min Range: -8.8739
Max Act: 8.3114. Min Act: -0.1700
Data Index: 7065851 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8739. Min Range: -8.8739
Max Act: 8.3114. Min Act: -0.1700
Data Index: 4354423 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8739. Min Range: -8.8739
Max Act: 8.3114. Min Act: -0.1700
Data Index: 971196 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8739. Min Range: -8.8739
Max Act: 8.1239. Min Act: -0.1700
Data Index: 5146048 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8739. Min Range: -8.8739
Max Act: 8.0926. Min Act: -0.1700
Data Index: 6664643 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8739. Min Range: -8.8739
Max Act: 8.0926. Min Act: -0.1700
Data Index: 1318535 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8739. Min Range: -8.8739
Max Act: 8.0301. Min Act: -0.1700
Data Index: 4007107 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8739. Min Range: -8.8739
Max Act: 7.9989. Min Act: -0.1700
Data Index: 2125993 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8739. Min Range: -8.8739
Max Act: 7.9676. Min Act: -0.1700
Data Index: 2283807 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8739. Min Range: -8.8739
Max Act: 7.9364. Min Act: -0.1700
Data Index: 5264415 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8739. Min Range: -8.8739
Max Act: 7.9364. Min Act: -0.1700
Data Index: 7365578 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8739. Min Range: -8.8739
Max Act: 7.9676. Min Act: -0.1700
Data Index: 362111 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8739. Min Range: -8.8739
Max Act: 7.9051. Min Act: -0.1700
Data Index: 4890747 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8739. Min Range: -8.8739
Max Act: 7.9051. Min Act: -0.1700
Data Index: 1609712 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8739. Min Range: -8.8739
Max Act: 7.9364. Min Act: -0.1700
Data Index: 3980058 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8739. Min Range: -8.8739
Max Act: 7.9051. Min Act: -0.1700
Data Index: 7286637 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8739. Min Range: -8.8739
Max Act: 7.9051. Min Act: -0.1700
Data Index: 3587570 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8739. Min Range: -8.8739
Max Act: 7.8739. Min Act: -0.1700
Data Index: 2768708 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19