Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4617. Min Range: -6.4617
Max Act: 6.4617. Min Act: -0.1700
Data Index: 2090541 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4617. Min Range: -6.4617
Max Act: 6.3367. Min Act: -0.1700
Data Index: 7178569 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4617. Min Range: -6.4617
Max Act: 6.2117. Min Act: -0.1700
Data Index: 2782766 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4617. Min Range: -6.4617
Max Act: 6.2429. Min Act: -0.1700
Data Index: 7642794 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4617. Min Range: -6.4617
Max Act: 6.1492. Min Act: -0.1700
Data Index: 4810798 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4617. Min Range: -6.4617
Max Act: 6.0554. Min Act: -0.1700
Data Index: 8336086 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4617. Min Range: -6.4617
Max Act: 6.0554. Min Act: -0.1700
Data Index: 8632640 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4617. Min Range: -6.4617
Max Act: 6.0242. Min Act: -0.1700
Data Index: 561717 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4617. Min Range: -6.4617
Max Act: 6.0554. Min Act: -0.1700
Data Index: 3145353 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4617. Min Range: -6.4617
Max Act: 6.0242. Min Act: -0.1700
Data Index: 6083721 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4617. Min Range: -6.4617
Max Act: 5.9617. Min Act: -0.1700
Data Index: 2560055 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4617. Min Range: -6.4617
Max Act: 5.9617. Min Act: -0.1700
Data Index: 1238297 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4617. Min Range: -6.4617
Max Act: 5.9304. Min Act: -0.1700
Data Index: 3958139 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4617. Min Range: -6.4617
Max Act: 5.9304. Min Act: -0.1700
Data Index: 4962217 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4617. Min Range: -6.4617
Max Act: 5.8367. Min Act: -0.1700
Data Index: 4242567 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4617. Min Range: -6.4617
Max Act: 5.8367. Min Act: -0.1700
Data Index: 5777479 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4617. Min Range: -6.4617
Max Act: 5.8054. Min Act: -0.1700
Data Index: 64542 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4617. Min Range: -6.4617
Max Act: 5.8367. Min Act: -0.1700
Data Index: 2353885 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4617. Min Range: -6.4617
Max Act: 5.7742. Min Act: -0.1700
Data Index: 3354582 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4617. Min Range: -6.4617
Max Act: 5.8054. Min Act: -0.1700
Data Index: 585614 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19