Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.6253. Min Act: -0.1700
Data Index: 4412432 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.5315. Min Act: -0.1700
Data Index: 8420161 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.5315. Min Act: -0.1700
Data Index: 2313362 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.4690. Min Act: -0.1700
Data Index: 7279991 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.3440. Min Act: -0.1700
Data Index: 3927057 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.3753. Min Act: -0.1700
Data Index: 5667729 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.3440. Min Act: -0.1700
Data Index: 4207657 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.3128. Min Act: -0.1700
Data Index: 5799827 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.3128. Min Act: -0.1700
Data Index: 1998445 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.2815. Min Act: -0.1700
Data Index: 45930 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.2503. Min Act: -0.1700
Data Index: 6121097 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.2503. Min Act: -0.1700
Data Index: 4150617 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.2503. Min Act: -0.1700
Data Index: 8195708 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.2190. Min Act: -0.1700
Data Index: 7580168 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.2190. Min Act: -0.1700
Data Index: 4887540 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.2190. Min Act: -0.1700
Data Index: 7911298 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.2190. Min Act: -0.1700
Data Index: 4325984 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.1565. Min Act: -0.1700
Data Index: 7127390 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.1878. Min Act: -0.1700
Data Index: 5569941 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6253. Min Range: -6.6253
Max Act: 6.1878. Min Act: -0.1700
Data Index: 7050755 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19