Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3186 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0491. Min Range: -1.0491
Max Act: 1.0491. Min Act: -0.1700
Data Index: 8571190 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.9969. Min Act: -0.1700
Data Index: 8048021 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.9882. Min Act: -0.1700
Data Index: 1693355 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.9278. Min Act: -0.1700
Data Index: 7962917 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.9106. Min Act: -0.1696
Data Index: 8761887 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8850. Min Act: -0.1700
Data Index: 7962920 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8765. Min Act: -0.1685
Data Index: 2808834 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8765. Min Act: -0.1700
Data Index: 858628 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8679. Min Act: -0.1699
Data Index: 7962922 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8425. Min Act: -0.1700
Data Index: 7962919 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8340. Min Act: -0.1700
Data Index: 7962921 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8256. Min Act: -0.1699
Data Index: 7951784 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8256. Min Act: -0.1672
Data Index: 7765383 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8256. Min Act: -0.1699
Data Index: 7962916 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8256. Min Act: -0.1699
Data Index: 7962918 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8172. Min Act: -0.1697
Data Index: 6441219 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8088. Min Act: -0.1671
Data Index: 4257025 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8088. Min Act: -0.1700
Data Index: 5178300 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8088. Min Act: -0.1697
Data Index: 365689 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0491. Min Range: -1.0491
Max Act: 0.8088. Min Act: -0.1694
Data Index: 7190202 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19