Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1838 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.6688. Min Act: -0.1700
Data Index: 450169 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.5751. Min Act: -0.1700
Data Index: 3044470 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.5438. Min Act: -0.1700
Data Index: 5489319 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.5438. Min Act: -0.1700
Data Index: 4319773 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.5438. Min Act: -0.1700
Data Index: 375216 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.5126. Min Act: -0.1700
Data Index: 1341022 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.4813. Min Act: -0.1700
Data Index: 6366318 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.4501. Min Act: -0.1700
Data Index: 6366319 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.4813. Min Act: -0.1700
Data Index: 2692637 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.4813. Min Act: -0.1700
Data Index: 2779907 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.4188. Min Act: -0.1700
Data Index: 1915183 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.4188. Min Act: -0.1700
Data Index: 5089605 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.3876. Min Act: -0.1700
Data Index: 1149636 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.3876. Min Act: -0.1700
Data Index: 632359 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.3876. Min Act: -0.1700
Data Index: 1040024 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.3876. Min Act: -0.1700
Data Index: 5737821 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.3876. Min Act: -0.1700
Data Index: 3834090 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.3563. Min Act: -0.1700
Data Index: 3239592 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.3563. Min Act: -0.1700
Data Index: 1518034 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6688. Min Range: -4.6688
Max Act: 4.2938. Min Act: -0.1700
Data Index: 5950676 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19