Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2262. Min Range: -3.2262
Max Act: 3.2262. Min Act: -0.1700
Data Index: 832338 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2262. Min Range: -3.2262
Max Act: 3.1633. Min Act: -0.1700
Data Index: 4098630 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2262. Min Range: -3.2262
Max Act: 3.1319. Min Act: -0.1700
Data Index: 2582026 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2262. Min Range: -3.2262
Max Act: 3.0846. Min Act: -0.1700
Data Index: 5741398 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2262. Min Range: -3.2262
Max Act: 3.0688. Min Act: -0.1700
Data Index: 4350035 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2262. Min Range: -3.2262
Max Act: 3.0530. Min Act: -0.1700
Data Index: 8779469 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2262. Min Range: -3.2262
Max Act: 3.0372. Min Act: -0.1700
Data Index: 7878297 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2262. Min Range: -3.2262
Max Act: 3.0215. Min Act: -0.1700
Data Index: 1657857 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2262. Min Range: -3.2262
Max Act: 3.0057. Min Act: -0.1700
Data Index: 8786653 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2262. Min Range: -3.2262
Max Act: 2.9899. Min Act: -0.1700
Data Index: 407112 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2262. Min Range: -3.2262
Max Act: 2.9899. Min Act: -0.1700
Data Index: 1644644 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2262. Min Range: -3.2262
Max Act: 2.9899. Min Act: -0.1700
Data Index: 3136062 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2262. Min Range: -3.2262
Max Act: 2.9740. Min Act: -0.1700
Data Index: 4500133 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2262. Min Range: -3.2262
Max Act: 2.9424. Min Act: -0.1700
Data Index: 352578 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2262. Min Range: -3.2262
Max Act: 2.9582. Min Act: -0.1700
Data Index: 1247261 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2262. Min Range: -3.2262
Max Act: 2.9424. Min Act: -0.1700
Data Index: 1467524 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2262. Min Range: -3.2262
Max Act: 2.9424. Min Act: -0.1700
Data Index: 6570108 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2262. Min Range: -3.2262
Max Act: 2.9424. Min Act: -0.1700
Data Index: 4822842 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2262. Min Range: -3.2262
Max Act: 2.9266. Min Act: -0.1700
Data Index: 819981 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2262. Min Range: -3.2262
Max Act: 2.9266. Min Act: -0.1700
Data Index: 594720 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19