Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4075 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4085. Min Range: -5.4085
Max Act: 5.4085. Min Act: -0.1700
Data Index: 2381226 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4085. Min Range: -5.4085
Max Act: 5.2835. Min Act: -0.1700
Data Index: 7796294 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4085. Min Range: -5.4085
Max Act: 5.2210. Min Act: -0.1700
Data Index: 4199340 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4085. Min Range: -5.4085
Max Act: 5.1585. Min Act: -0.1700
Data Index: 204916 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4085. Min Range: -5.4085
Max Act: 5.1273. Min Act: -0.1700
Data Index: 3827553 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4085. Min Range: -5.4085
Max Act: 5.0960. Min Act: -0.1700
Data Index: 7796292 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4085. Min Range: -5.4085
Max Act: 5.0648. Min Act: -0.1700
Data Index: 1337848 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4085. Min Range: -5.4085
Max Act: 5.0335. Min Act: -0.1700
Data Index: 5230885 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4085. Min Range: -5.4085
Max Act: 5.0023. Min Act: -0.1700
Data Index: 3194560 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4085. Min Range: -5.4085
Max Act: 5.0023. Min Act: -0.1700
Data Index: 5900693 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4085. Min Range: -5.4085
Max Act: 4.9710. Min Act: -0.1700
Data Index: 600674 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4085. Min Range: -5.4085
Max Act: 4.9710. Min Act: -0.1700
Data Index: 320620 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4085. Min Range: -5.4085
Max Act: 4.9710. Min Act: -0.1700
Data Index: 5281602 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4085. Min Range: -5.4085
Max Act: 4.9398. Min Act: -0.1700
Data Index: 4199341 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4085. Min Range: -5.4085
Max Act: 4.9398. Min Act: -0.1700
Data Index: 5212043 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4085. Min Range: -5.4085
Max Act: 4.9085. Min Act: -0.1700
Data Index: 2802887 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4085. Min Range: -5.4085
Max Act: 4.9085. Min Act: -0.1700
Data Index: 4928694 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4085. Min Range: -5.4085
Max Act: 4.9085. Min Act: -0.1700
Data Index: 5127315 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4085. Min Range: -5.4085
Max Act: 4.9085. Min Act: -0.1700
Data Index: 4639598 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4085. Min Range: -5.4085
Max Act: 4.8773. Min Act: -0.1700
Data Index: 4060768 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19