Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 654 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.7551. Min Act: -0.1700
Data Index: 1518244 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.6926. Min Act: -0.1700
Data Index: 6650377 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5989. Min Act: -0.1700
Data Index: 7133578 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.6301. Min Act: -0.1700
Data Index: 5319919 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5676. Min Act: -0.1700
Data Index: 5401600 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5989. Min Act: -0.1700
Data Index: 3970673 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.6301. Min Act: -0.1700
Data Index: 7085157 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5989. Min Act: -0.1700
Data Index: 6525967 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5989. Min Act: -0.1700
Data Index: 5396582 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5989. Min Act: -0.1700
Data Index: 5197365 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5989. Min Act: -0.1700
Data Index: 7848524 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5676. Min Act: -0.1700
Data Index: 7711019 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5989. Min Act: -0.1700
Data Index: 4593481 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5676. Min Act: -0.1700
Data Index: 6058130 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5364. Min Act: -0.1700
Data Index: 6594503 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5364. Min Act: -0.1700
Data Index: 8467799 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5676. Min Act: -0.1700
Data Index: 4831428 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5051. Min Act: -0.1700
Data Index: 6198468 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5364. Min Act: -0.1700
Data Index: 4513375 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7551. Min Range: -4.7551
Max Act: 4.5051. Min Act: -0.1700
Data Index: 7624419 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19