Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 564 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.7792. Min Act: -0.1700
Data Index: 3759975 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.5917. Min Act: -0.1700
Data Index: 5437974 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.4042. Min Act: -0.1700
Data Index: 6866371 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.4042. Min Act: -0.1700
Data Index: 5563697 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.3730. Min Act: -0.1700
Data Index: 3649031 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.2792. Min Act: -0.1700
Data Index: 4912213 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.2480. Min Act: -0.1700
Data Index: 3668217 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.2167. Min Act: -0.1700
Data Index: 5129238 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.2167. Min Act: -0.1700
Data Index: 2991097 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.2167. Min Act: -0.1700
Data Index: 2698961 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.1855. Min Act: -0.1700
Data Index: 8216677 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.1542. Min Act: -0.1700
Data Index: 4183033 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.1542. Min Act: -0.1700
Data Index: 2895434 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.1542. Min Act: -0.1700
Data Index: 6593093 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.1542. Min Act: -0.1700
Data Index: 6497010 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.1542. Min Act: -0.1700
Data Index: 6459283 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.1230. Min Act: -0.1700
Data Index: 6084630 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.1230. Min Act: -0.1700
Data Index: 384540 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.1230. Min Act: -0.1700
Data Index: 6333975 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7792. Min Range: -7.7792
Max Act: 7.0917. Min Act: -0.1700
Data Index: 5425133 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19