Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2635 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3269. Min Range: -6.3269
Max Act: 6.3269. Min Act: -0.1700
Data Index: 5402576 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.9519. Min Act: -0.1700
Data Index: 1729993 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.7644. Min Act: -0.1700
Data Index: 8808654 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.7019. Min Act: -0.1700
Data Index: 4150513 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.6394. Min Act: -0.1700
Data Index: 5036367 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.5769. Min Act: -0.1700
Data Index: 8551698 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.5769. Min Act: -0.1700
Data Index: 2482874 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.5456. Min Act: -0.1700
Data Index: 2667327 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.5456. Min Act: -0.1700
Data Index: 3150196 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.4831. Min Act: -0.1700
Data Index: 4188165 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.4206. Min Act: -0.1700
Data Index: 2079142 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.4519. Min Act: -0.1700
Data Index: 1120297 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.4206. Min Act: -0.1700
Data Index: 6470420 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.4519. Min Act: -0.1700
Data Index: 2790965 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.4206. Min Act: -0.1700
Data Index: 1894355 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.4206. Min Act: -0.1700
Data Index: 239880 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.4206. Min Act: -0.1700
Data Index: 4726471 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.3894. Min Act: -0.1700
Data Index: 8125167 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.3894. Min Act: -0.1700
Data Index: 7281077 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3269. Min Range: -6.3269
Max Act: 5.3269. Min Act: -0.1700
Data Index: 4882875 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19