Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1817 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.7696. Min Act: -0.1700
Data Index: 8092669 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.7071. Min Act: -0.1700
Data Index: 1911752 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.6759. Min Act: -0.1700
Data Index: 4637640 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.6134. Min Act: -0.1700
Data Index: 2826864 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.6134. Min Act: -0.1700
Data Index: 3198977 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.6446. Min Act: -0.1700
Data Index: 1575559 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.6446. Min Act: -0.1700
Data Index: 419735 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.6134. Min Act: -0.1700
Data Index: 226158 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.5821. Min Act: -0.1700
Data Index: 3285650 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.5821. Min Act: -0.1700
Data Index: 4532908 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.5509. Min Act: -0.1700
Data Index: 7422280 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.5821. Min Act: -0.1700
Data Index: 5479292 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.5821. Min Act: -0.1700
Data Index: 2160738 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.5821. Min Act: -0.1700
Data Index: 4313006 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.5509. Min Act: -0.1700
Data Index: 2041844 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.5509. Min Act: -0.1700
Data Index: 5473930 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.5509. Min Act: -0.1700
Data Index: 995272 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.5509. Min Act: -0.1700
Data Index: 6384912 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.5509. Min Act: -0.1700
Data Index: 8207366 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7696. Min Range: -6.7696
Max Act: 6.5509. Min Act: -0.1700
Data Index: 1684090 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19