Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4731 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.7847. Min Act: -0.1700
Data Index: 7847146 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.7535. Min Act: -0.1700
Data Index: 4462018 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.5660. Min Act: -0.1700
Data Index: 2456427 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.5035. Min Act: -0.1700
Data Index: 1021986 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.4722. Min Act: -0.1700
Data Index: 2794530 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.4410. Min Act: -0.1700
Data Index: 2400585 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.4410. Min Act: -0.1700
Data Index: 26044 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.4410. Min Act: -0.1700
Data Index: 6177038 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.4097. Min Act: -0.1700
Data Index: 7436905 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.4097. Min Act: -0.1700
Data Index: 566933 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.4410. Min Act: -0.1700
Data Index: 6599520 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.3785. Min Act: -0.1700
Data Index: 6914435 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.3785. Min Act: -0.1700
Data Index: 1506127 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.3785. Min Act: -0.1700
Data Index: 1337681 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.3785. Min Act: -0.1700
Data Index: 6539074 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.3785. Min Act: -0.1700
Data Index: 7070943 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.3472. Min Act: -0.1700
Data Index: 1417752 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.3472. Min Act: -0.1700
Data Index: 3761579 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.3785. Min Act: -0.1700
Data Index: 3148722 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7847. Min Range: -6.7847
Max Act: 6.3472. Min Act: -0.1700
Data Index: 6486007 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19