Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3295 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.5224. Min Act: -0.1700
Data Index: 3279350 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.5224. Min Act: -0.1700
Data Index: 7474400 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.4911. Min Act: -0.1700
Data Index: 236401 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.4286. Min Act: -0.1700
Data Index: 7916121 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.3974. Min Act: -0.1700
Data Index: 7249742 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.3661. Min Act: -0.1700
Data Index: 8784086 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.3661. Min Act: -0.1700
Data Index: 6967120 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.2724. Min Act: -0.1700
Data Index: 4519666 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.2099. Min Act: -0.1700
Data Index: 7504428 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.2099. Min Act: -0.1700
Data Index: 5726647 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.2099. Min Act: -0.1700
Data Index: 8533712 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.2099. Min Act: -0.1700
Data Index: 3453406 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.2099. Min Act: -0.1700
Data Index: 5608843 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.1786. Min Act: -0.1700
Data Index: 4365465 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.2099. Min Act: -0.1700
Data Index: 2306617 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.1474. Min Act: -0.1700
Data Index: 1120686 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.1474. Min Act: -0.1700
Data Index: 8496861 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.1474. Min Act: -0.1700
Data Index: 6474620 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.1474. Min Act: -0.1700
Data Index: 1120685 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5224. Min Range: -4.5224
Max Act: 4.1474. Min Act: -0.1700
Data Index: 8373499 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19