Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5551 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.5256. Min Act: -0.1700
Data Index: 8255494 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.5256. Min Act: -0.1700
Data Index: 5396710 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.4631. Min Act: -0.1700
Data Index: 8255492 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.4631. Min Act: -0.1700
Data Index: 8255491 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.4943. Min Act: -0.1700
Data Index: 8255493 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.4006. Min Act: -0.1700
Data Index: 5396713 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.3693. Min Act: -0.1700
Data Index: 8618583 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.3381. Min Act: -0.1700
Data Index: 5694706 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.2756. Min Act: -0.1700
Data Index: 5396715 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.2756. Min Act: -0.1700
Data Index: 4702342 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.2131. Min Act: -0.1700
Data Index: 5396711 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.1506. Min Act: -0.1700
Data Index: 4473804 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.1506. Min Act: -0.1700
Data Index: 6752880 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.1506. Min Act: -0.1700
Data Index: 2393660 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.1506. Min Act: -0.1700
Data Index: 1987089 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.1193. Min Act: -0.1700
Data Index: 4473803 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.1193. Min Act: -0.1700
Data Index: 950290 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.0881. Min Act: -0.1700
Data Index: 7920239 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.0568. Min Act: -0.1700
Data Index: 2030319 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5256. Min Range: -5.5256
Max Act: 5.0568. Min Act: -0.1700
Data Index: 7978174 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19