Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4589 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.5445. Min Act: -0.1700
Data Index: 7570472 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.5132. Min Act: -0.1700
Data Index: 2837368 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.5132. Min Act: -0.1700
Data Index: 2490093 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.4820. Min Act: -0.1700
Data Index: 2878535 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.3882. Min Act: -0.1700
Data Index: 6973329 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.4195. Min Act: -0.1700
Data Index: 5430703 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.3570. Min Act: -0.1700
Data Index: 6317954 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.3570. Min Act: -0.1700
Data Index: 6082319 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.3570. Min Act: -0.1700
Data Index: 6187569 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.3257. Min Act: -0.1700
Data Index: 4990580 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.2632. Min Act: -0.1700
Data Index: 8717967 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.2632. Min Act: -0.1700
Data Index: 5571399 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.2632. Min Act: -0.1700
Data Index: 5398509 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.2632. Min Act: -0.1700
Data Index: 6130260 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.2632. Min Act: -0.1700
Data Index: 2655263 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.2320. Min Act: -0.1699
Data Index: 2575979 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.2007. Min Act: -0.1700
Data Index: 3265229 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.2007. Min Act: -0.1700
Data Index: 1517705 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.1695. Min Act: -0.1700
Data Index: 1837990 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5445. Min Range: -5.5445
Max Act: 5.1695. Min Act: -0.1700
Data Index: 4378064 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19