Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1263. Min Range: -7.1263
Max Act: 7.1263. Min Act: -0.1700
Data Index: 590561 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1263. Min Range: -7.1263
Max Act: 7.0950. Min Act: -0.1700
Data Index: 472486 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.7513. Min Act: -0.1700
Data Index: 8176377 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.7200. Min Act: -0.1700
Data Index: 5863713 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.6888. Min Act: -0.1700
Data Index: 1629009 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.6888. Min Act: -0.1700
Data Index: 60166 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.5950. Min Act: -0.1700
Data Index: 5191189 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.5950. Min Act: -0.1700
Data Index: 4838669 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.5638. Min Act: -0.1700
Data Index: 1500263 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.5638. Min Act: -0.1700
Data Index: 571707 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.5638. Min Act: -0.1700
Data Index: 6304418 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.5325. Min Act: -0.1700
Data Index: 804361 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.5013. Min Act: -0.1700
Data Index: 4134251 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.4700. Min Act: -0.1700
Data Index: 768004 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.4075. Min Act: -0.1700
Data Index: 7236698 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.4388. Min Act: -0.1700
Data Index: 6435535 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.4075. Min Act: -0.1700
Data Index: 2011667 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.3450. Min Act: -0.1700
Data Index: 4710065 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.2825. Min Act: -0.1700
Data Index: 2015153 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1263. Min Range: -7.1263
Max Act: 6.2513. Min Act: -0.1700
Data Index: 7112987 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19