Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4075 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0405. Min Range: -4.0405
Max Act: 4.0405. Min Act: -0.1700
Data Index: 2596390 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0405. Min Range: -4.0405
Max Act: 4.0093. Min Act: -0.1700
Data Index: 1913163 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.9468. Min Act: -0.1700
Data Index: 6615659 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.9468. Min Act: -0.1700
Data Index: 3554820 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.9155. Min Act: -0.1700
Data Index: 492239 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.8530. Min Act: -0.1700
Data Index: 7637172 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.8842. Min Act: -0.1700
Data Index: 46295 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.8842. Min Act: -0.1700
Data Index: 8770498 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.8842. Min Act: -0.1700
Data Index: 6211982 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.8217. Min Act: -0.1700
Data Index: 5135591 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.8217. Min Act: -0.1700
Data Index: 4052494 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.8217. Min Act: -0.1700
Data Index: 8407489 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.8217. Min Act: -0.1700
Data Index: 4938501 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.7591. Min Act: -0.1700
Data Index: 3222958 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.7904. Min Act: -0.1700
Data Index: 3161395 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.7904. Min Act: -0.1700
Data Index: 4650761 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.7904. Min Act: -0.1700
Data Index: 3407415 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.7591. Min Act: -0.1700
Data Index: 2936971 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.7435. Min Act: -0.1700
Data Index: 218855 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0405. Min Range: -4.0405
Max Act: 3.7435. Min Act: -0.1700
Data Index: 833485 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19