Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3140 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.9109. Min Act: -0.1700
Data Index: 4382261 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.8796. Min Act: -0.1700
Data Index: 2160164 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.8171. Min Act: -0.1700
Data Index: 5739246 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.8171. Min Act: -0.1700
Data Index: 447236 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.8171. Min Act: -0.1700
Data Index: 6304618 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.7546. Min Act: -0.1700
Data Index: 5322799 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.7234. Min Act: -0.1700
Data Index: 6633375 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.6609. Min Act: -0.1700
Data Index: 8362705 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.6609. Min Act: -0.1700
Data Index: 8278526 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.6609. Min Act: -0.1700
Data Index: 6838020 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.6296. Min Act: -0.1700
Data Index: 3994157 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.6296. Min Act: -0.1700
Data Index: 8276499 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.6296. Min Act: -0.1700
Data Index: 4382260 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.6296. Min Act: -0.1700
Data Index: 3849809 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.5984. Min Act: -0.1700
Data Index: 8392306 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.5671. Min Act: -0.1700
Data Index: 2407624 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.6296. Min Act: -0.1700
Data Index: 1822479 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.5984. Min Act: -0.1700
Data Index: 6913716 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.5984. Min Act: -0.1700
Data Index: 3837455 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9109. Min Range: -6.9109
Max Act: 6.5359. Min Act: -0.1700
Data Index: 1011958 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19