Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1601 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.6621. Min Act: -0.1700
Data Index: 806427 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.5371. Min Act: -0.1700
Data Index: 1786299 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.4746. Min Act: -0.1700
Data Index: 4838045 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.3809. Min Act: -0.1700
Data Index: 1624648 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.2246. Min Act: -0.1700
Data Index: 1305312 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.1621. Min Act: -0.1700
Data Index: 5285424 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.0996. Min Act: -0.1700
Data Index: 2714288 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.0996. Min Act: -0.1700
Data Index: 4064631 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.0684. Min Act: -0.1700
Data Index: 6824504 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.0684. Min Act: -0.1700
Data Index: 8589820 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.0371. Min Act: -0.1700
Data Index: 952321 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.0371. Min Act: -0.1700
Data Index: 8343400 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.0059. Min Act: -0.1700
Data Index: 3575599 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6621. Min Range: -6.6621
Max Act: 5.9746. Min Act: -0.1700
Data Index: 4453951 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6621. Min Range: -6.6621
Max Act: 5.9746. Min Act: -0.1700
Data Index: 8264603 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6621. Min Range: -6.6621
Max Act: 5.9746. Min Act: -0.1700
Data Index: 5715230 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6621. Min Range: -6.6621
Max Act: 6.0059. Min Act: -0.1700
Data Index: 3862579 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6621. Min Range: -6.6621
Max Act: 5.9434. Min Act: -0.1700
Data Index: 6051937 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6621. Min Range: -6.6621
Max Act: 5.9434. Min Act: -0.1700
Data Index: 7245566 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6621. Min Range: -6.6621
Max Act: 5.9121. Min Act: -0.1700
Data Index: 7471097 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19