Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1515 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.6422. Min Act: -0.1700
Data Index: 8781702 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.6109. Min Act: -0.1700
Data Index: 5828824 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.5796. Min Act: -0.1700
Data Index: 7950756 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.5170. Min Act: -0.1700
Data Index: 6258276 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.4700. Min Act: -0.1700
Data Index: 8730580 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.4544. Min Act: -0.1700
Data Index: 3788585 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.4700. Min Act: -0.1700
Data Index: 586556 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.4857. Min Act: -0.1700
Data Index: 5265473 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.5013. Min Act: -0.1700
Data Index: 4972497 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.4387. Min Act: -0.1700
Data Index: 3040516 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.4544. Min Act: -0.1700
Data Index: 1997535 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.4387. Min Act: -0.1700
Data Index: 3589325 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.4230. Min Act: -0.1700
Data Index: 4154830 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.4387. Min Act: -0.1700
Data Index: 3350621 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.4387. Min Act: -0.1700
Data Index: 8290760 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.4073. Min Act: -0.1700
Data Index: 2189092 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.3917. Min Act: -0.1700
Data Index: 7227259 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.4230. Min Act: -0.1700
Data Index: 5936738 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.3917. Min Act: -0.1700
Data Index: 8270843 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6422. Min Range: -3.6422
Max Act: 3.3917. Min Act: -0.1700
Data Index: 5868489 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19