Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1336 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.8444. Min Act: -0.1700
Data Index: 1398700 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.7929. Min Act: -0.1699
Data Index: 1398699 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.7325. Min Act: -0.1700
Data Index: 6214503 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.6631. Min Act: -0.1700
Data Index: 1398698 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.6370. Min Act: -0.1700
Data Index: 576015 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.6196. Min Act: -0.1700
Data Index: 1398697 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.6196. Min Act: -0.1700
Data Index: 4334413 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.6109. Min Act: -0.1700
Data Index: 4413480 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.6109. Min Act: -0.1700
Data Index: 2727170 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.6109. Min Act: -0.1700
Data Index: 3083256 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.6021. Min Act: -0.1700
Data Index: 7020915 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.5847. Min Act: -0.1700
Data Index: 3704968 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.5934. Min Act: -0.1700
Data Index: 3945871 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.5759. Min Act: -0.1700
Data Index: 1393770 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.5672. Min Act: -0.1700
Data Index: 2011613 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.5759. Min Act: -0.1700
Data Index: 3888553 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.5584. Min Act: -0.1700
Data Index: 7103111 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.5584. Min Act: -0.1700
Data Index: 6879065 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.5497. Min Act: -0.1700
Data Index: 1634842 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8444. Min Range: -1.8444
Max Act: 1.5584. Min Act: -0.1699
Data Index: 2724551 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19