Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 409 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3224. Min Range: -5.3224
Max Act: 5.3224. Min Act: -0.1700
Data Index: 5130586 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3224. Min Range: -5.3224
Max Act: 5.2599. Min Act: -0.1700
Data Index: 5998994 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3224. Min Range: -5.3224
Max Act: 5.0724. Min Act: -0.1700
Data Index: 4734870 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3224. Min Range: -5.3224
Max Act: 5.0412. Min Act: -0.1700
Data Index: 396926 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3224. Min Range: -5.3224
Max Act: 5.0099. Min Act: -0.1700
Data Index: 3716060 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3224. Min Range: -5.3224
Max Act: 5.0099. Min Act: -0.1700
Data Index: 3552858 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3224. Min Range: -5.3224
Max Act: 4.9474. Min Act: -0.1700
Data Index: 6809068 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3224. Min Range: -5.3224
Max Act: 4.9787. Min Act: -0.1700
Data Index: 4095814 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3224. Min Range: -5.3224
Max Act: 5.0099. Min Act: -0.1700
Data Index: 3649315 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3224. Min Range: -5.3224
Max Act: 4.9474. Min Act: -0.1700
Data Index: 711466 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3224. Min Range: -5.3224
Max Act: 4.9474. Min Act: -0.1699
Data Index: 4252042 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3224. Min Range: -5.3224
Max Act: 4.9162. Min Act: -0.1700
Data Index: 5380932 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3224. Min Range: -5.3224
Max Act: 4.9162. Min Act: -0.1700
Data Index: 6973546 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3224. Min Range: -5.3224
Max Act: 4.9162. Min Act: -0.1700
Data Index: 5982729 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3224. Min Range: -5.3224
Max Act: 4.9162. Min Act: -0.1700
Data Index: 3552859 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3224. Min Range: -5.3224
Max Act: 4.8849. Min Act: -0.1700
Data Index: 2242673 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3224. Min Range: -5.3224
Max Act: 4.8224. Min Act: -0.1700
Data Index: 4329953 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3224. Min Range: -5.3224
Max Act: 4.8537. Min Act: -0.1700
Data Index: 6643181 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3224. Min Range: -5.3224
Max Act: 4.8537. Min Act: -0.1700
Data Index: 1519106 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3224. Min Range: -5.3224
Max Act: 4.8537. Min Act: -0.1700
Data Index: 4464480 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19