Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6026 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3444. Min Range: -4.3444
Max Act: 4.3444. Min Act: -0.1700
Data Index: 657893 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3444. Min Range: -4.3444
Max Act: 4.1881. Min Act: -0.1700
Data Index: 657892 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3444. Min Range: -4.3444
Max Act: 4.0944. Min Act: -0.1700
Data Index: 657890 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3444. Min Range: -4.3444
Max Act: 4.0631. Min Act: -0.1700
Data Index: 8807917 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3444. Min Range: -4.3444
Max Act: 4.0631. Min Act: -0.1700
Data Index: 2976109 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3444. Min Range: -4.3444
Max Act: 4.0006. Min Act: -0.1700
Data Index: 7870227 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3444. Min Range: -4.3444
Max Act: 4.0006. Min Act: -0.1700
Data Index: 30897 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3444. Min Range: -4.3444
Max Act: 3.9693. Min Act: -0.1700
Data Index: 7870226 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3444. Min Range: -4.3444
Max Act: 4.0006. Min Act: -0.1700
Data Index: 657891 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3444. Min Range: -4.3444
Max Act: 3.9381. Min Act: -0.1700
Data Index: 3700647 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3444. Min Range: -4.3444
Max Act: 3.9068. Min Act: -0.1700
Data Index: 8741412 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3444. Min Range: -4.3444
Max Act: 3.9068. Min Act: -0.1700
Data Index: 38256 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3444. Min Range: -4.3444
Max Act: 3.9068. Min Act: -0.1700
Data Index: 1348701 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3444. Min Range: -4.3444
Max Act: 3.9068. Min Act: -0.1700
Data Index: 5431527 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3444. Min Range: -4.3444
Max Act: 3.9068. Min Act: -0.1700
Data Index: 5302967 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3444. Min Range: -4.3444
Max Act: 3.9068. Min Act: -0.1700
Data Index: 4960769 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3444. Min Range: -4.3444
Max Act: 3.8755. Min Act: -0.1700
Data Index: 7280762 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3444. Min Range: -4.3444
Max Act: 3.8755. Min Act: -0.1700
Data Index: 943166 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3444. Min Range: -4.3444
Max Act: 3.8755. Min Act: -0.1700
Data Index: 657888 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3444. Min Range: -4.3444
Max Act: 3.8755. Min Act: -0.1700
Data Index: 2447567 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19