Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2421 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.4753. Min Act: -0.1700
Data Index: 1581281 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.2378. Min Act: -0.1700
Data Index: 4562643 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.2295. Min Act: -0.1700
Data Index: 7214405 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.1381. Min Act: -0.1699
Data Index: 8716834 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.1214. Min Act: -0.1698
Data Index: 6911995 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0880. Min Act: -0.1700
Data Index: 1860330 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.1047. Min Act: -0.1698
Data Index: 537306 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0796. Min Act: -0.1700
Data Index: 2406016 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0880. Min Act: -0.1700
Data Index: 473766 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0712. Min Act: -0.1606
Data Index: 8702676 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0880. Min Act: -0.1700
Data Index: 996669 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0628. Min Act: -0.1700
Data Index: 3785346 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0544. Min Act: -0.1700
Data Index: 6581035 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0544. Min Act: -0.1680
Data Index: 3446585 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0291. Min Act: -0.1700
Data Index: 8702678 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0460. Min Act: -0.1700
Data Index: 6020149 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0376. Min Act: -0.1700
Data Index: 8702679 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0207. Min Act: -0.1700
Data Index: 4756370 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0038. Min Act: -0.1686
Data Index: 8702681 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4753. Min Range: -2.4753
Max Act: 2.0123. Min Act: -0.1700
Data Index: 8702691 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19