Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4445 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2738. Min Range: -8.2738
Max Act: 8.2738. Min Act: -0.1700
Data Index: 6939527 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.9613. Min Act: -0.1700
Data Index: 1745235 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.8988. Min Act: -0.1700
Data Index: 1619112 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.7738. Min Act: -0.1700
Data Index: 4075571 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.7738. Min Act: -0.1700
Data Index: 6145099 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.7738. Min Act: -0.1700
Data Index: 4397044 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.7113. Min Act: -0.1700
Data Index: 4519407 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.7425. Min Act: -0.1700
Data Index: 4626249 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.6800. Min Act: -0.1700
Data Index: 3915614 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.6800. Min Act: -0.1700
Data Index: 4013114 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.6800. Min Act: -0.1700
Data Index: 5864334 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.6488. Min Act: -0.1700
Data Index: 3177393 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.6800. Min Act: -0.1700
Data Index: 4817095 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.6488. Min Act: -0.1700
Data Index: 8560141 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.6175. Min Act: -0.1700
Data Index: 474251 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.6175. Min Act: -0.1700
Data Index: 2639817 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.5863. Min Act: -0.1700
Data Index: 1752775 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.5550. Min Act: -0.1700
Data Index: 6574440 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.5550. Min Act: -0.1700
Data Index: 1856220 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2738. Min Range: -8.2738
Max Act: 7.5238. Min Act: -0.1700
Data Index: 5662434 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19