Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2252 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.7532. Min Act: -0.1700
Data Index: 3375006 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.7532. Min Act: -0.1700
Data Index: 3083237 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.7532. Min Act: -0.1700
Data Index: 1376959 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.6907. Min Act: -0.1700
Data Index: 1885872 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.6282. Min Act: -0.1700
Data Index: 6442234 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.6907. Min Act: -0.1700
Data Index: 2409783 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.6282. Min Act: -0.1700
Data Index: 3220405 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.6282. Min Act: -0.1700
Data Index: 6934368 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.6282. Min Act: -0.1700
Data Index: 5657256 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.6282. Min Act: -0.1700
Data Index: 6979871 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.5657. Min Act: -0.1700
Data Index: 2216521 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.5657. Min Act: -0.1700
Data Index: 7617931 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.5657. Min Act: -0.1700
Data Index: 4451261 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.5657. Min Act: -0.1700
Data Index: 3808813 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.5032. Min Act: -0.1700
Data Index: 8350374 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.5032. Min Act: -0.1700
Data Index: 4828139 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.4407. Min Act: -0.1700
Data Index: 5926581 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.4407. Min Act: -0.1700
Data Index: 3079202 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.4407. Min Act: -0.1700
Data Index: 5022524 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7532. Min Range: -9.7532
Max Act: 9.4407. Min Act: -0.1700
Data Index: 6055210 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19