Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4850 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.7104. Min Act: -0.1700
Data Index: 5010832 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.6784. Min Act: -0.1700
Data Index: 8375174 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.6142. Min Act: -0.1700
Data Index: 1224357 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5498. Min Act: -0.1700
Data Index: 4399708 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5659. Min Act: -0.1700
Data Index: 2150694 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5498. Min Act: -0.1700
Data Index: 1220729 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5498. Min Act: -0.1700
Data Index: 850033 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5498. Min Act: -0.1700
Data Index: 5824608 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5498. Min Act: -0.1700
Data Index: 2623230 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5336. Min Act: -0.1700
Data Index: 6377790 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5336. Min Act: -0.1700
Data Index: 8633556 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5336. Min Act: -0.1700
Data Index: 4567666 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5174. Min Act: -0.1700
Data Index: 6274501 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5012. Min Act: -0.1700
Data Index: 2859998 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5012. Min Act: -0.1700
Data Index: 3350172 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5012. Min Act: -0.1700
Data Index: 3733735 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5012. Min Act: -0.1700
Data Index: 4363607 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5174. Min Act: -0.1700
Data Index: 4702348 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.5012. Min Act: -0.1700
Data Index: 2252831 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7104. Min Range: -2.7104
Max Act: 2.4850. Min Act: -0.1700
Data Index: 6753152 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19