Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4574 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.4491. Min Act: -0.1700
Data Index: 6158937 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.3241. Min Act: -0.1700
Data Index: 8433852 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1678. Min Act: -0.1700
Data Index: 4429214 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1053. Min Act: -0.1700
Data Index: 5949070 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1053. Min Act: -0.1700
Data Index: 3730402 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1053. Min Act: -0.1700
Data Index: 4459104 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1053. Min Act: -0.1700
Data Index: 3603552 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.0740. Min Act: -0.1700
Data Index: 3402902 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1053. Min Act: -0.1700
Data Index: 1356269 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1053. Min Act: -0.1700
Data Index: 2017198 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.0115. Min Act: -0.1700
Data Index: 7413897 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.0428. Min Act: -0.1700
Data Index: 6387670 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.0428. Min Act: -0.1700
Data Index: 6673499 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.0115. Min Act: -0.1700
Data Index: 7573449 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.0115. Min Act: -0.1700
Data Index: 7254343 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.0115. Min Act: -0.1700
Data Index: 4574398 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4491. Min Range: -4.4491
Max Act: 3.9490. Min Act: -0.1700
Data Index: 4702250 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4491. Min Range: -4.4491
Max Act: 3.9803. Min Act: -0.1700
Data Index: 6325573 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4491. Min Range: -4.4491
Max Act: 3.9803. Min Act: -0.1700
Data Index: 1884206 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4491. Min Range: -4.4491
Max Act: 3.9490. Min Act: -0.1700
Data Index: 2499355 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19