Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 967 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9917. Min Act: -0.1700
Data Index: 3710086 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9744. Min Act: -0.1699
Data Index: 6382498 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9831. Min Act: -0.1695
Data Index: 6586241 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9658. Min Act: -0.1700
Data Index: 32490 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9485. Min Act: -0.1700
Data Index: 8821597 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9485. Min Act: -0.1698
Data Index: 3498700 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9571. Min Act: -0.1700
Data Index: 8186394 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9227. Min Act: -0.1700
Data Index: 7007354 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9399. Min Act: -0.1688
Data Index: 3208243 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9571. Min Act: -0.1700
Data Index: 4592830 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9313. Min Act: -0.1698
Data Index: 2587266 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9227. Min Act: -0.1700
Data Index: 4436394 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9227. Min Act: -0.1700
Data Index: 403137 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9227. Min Act: -0.1700
Data Index: 47349 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9227. Min Act: -0.1682
Data Index: 1640184 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9313. Min Act: -0.1700
Data Index: 6698685 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9313. Min Act: -0.1681
Data Index: 5265101 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9055. Min Act: -0.1692
Data Index: 5891062 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.9227. Min Act: -0.1700
Data Index: 2082969 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9917. Min Range: -0.9917
Max Act: 0.8970. Min Act: -0.1700
Data Index: 3661762 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19