Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 580 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.7249. Min Act: -0.1700
Data Index: 7758546 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.6624. Min Act: -0.1700
Data Index: 4323616 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.5999. Min Act: -0.1700
Data Index: 7458479 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.5062. Min Act: -0.1700
Data Index: 7458476 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.5687. Min Act: -0.1700
Data Index: 4323614 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.5062. Min Act: -0.1700
Data Index: 7758544 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.4749. Min Act: -0.1700
Data Index: 460971 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.4437. Min Act: -0.1700
Data Index: 6103360 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.2874. Min Act: -0.1700
Data Index: 8702002 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.2562. Min Act: -0.1700
Data Index: 7003662 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.2249. Min Act: -0.1700
Data Index: 1335641 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.1937. Min Act: -0.1700
Data Index: 2963487 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.1937. Min Act: -0.1700
Data Index: 1884290 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.1624. Min Act: -0.1700
Data Index: 3936003 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.1937. Min Act: -0.1700
Data Index: 4717819 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.1312. Min Act: -0.1700
Data Index: 3067332 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.1312. Min Act: -0.1700
Data Index: 6996234 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.1312. Min Act: -0.1700
Data Index: 5835947 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.0999. Min Act: -0.1700
Data Index: 3418942 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7249. Min Range: -5.7249
Max Act: 5.0999. Min Act: -0.1700
Data Index: 352948 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19