Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4355 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.7899. Min Act: -0.1700
Data Index: 4149926 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.7587. Min Act: -0.1700
Data Index: 7707833 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.7274. Min Act: -0.1700
Data Index: 7069111 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.6962. Min Act: -0.1700
Data Index: 8708522 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.6649. Min Act: -0.1700
Data Index: 4927028 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.5712. Min Act: -0.1700
Data Index: 1376667 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.6024. Min Act: -0.1700
Data Index: 7455216 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.6024. Min Act: -0.1700
Data Index: 1919423 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.5712. Min Act: -0.1700
Data Index: 8359287 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.5712. Min Act: -0.1700
Data Index: 6722507 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.5712. Min Act: -0.1700
Data Index: 3829947 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.5712. Min Act: -0.1700
Data Index: 8734743 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.5712. Min Act: -0.1700
Data Index: 5632520 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.5712. Min Act: -0.1700
Data Index: 6319997 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.5399. Min Act: -0.1700
Data Index: 6970737 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.5399. Min Act: -0.1700
Data Index: 2400787 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.5399. Min Act: -0.1700
Data Index: 5898288 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.5087. Min Act: -0.1700
Data Index: 7920636 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.5399. Min Act: -0.1700
Data Index: 4830976 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7899. Min Range: -5.7899
Max Act: 5.5399. Min Act: -0.1700
Data Index: 608528 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19