Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0526. Min Range: -5.0526
Max Act: 5.0526. Min Act: -0.1700
Data Index: 3291216 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.8026. Min Act: -0.1700
Data Index: 823848 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.7713. Min Act: -0.1700
Data Index: 1967185 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.6463. Min Act: -0.1700
Data Index: 6040772 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.6151. Min Act: -0.1700
Data Index: 8351465 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.6151. Min Act: -0.1700
Data Index: 3908244 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.5526. Min Act: -0.1700
Data Index: 5343659 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.5213. Min Act: -0.1700
Data Index: 376133 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.5526. Min Act: -0.1700
Data Index: 240115 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.5526. Min Act: -0.1700
Data Index: 4383409 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.5526. Min Act: -0.1700
Data Index: 8823273 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.5526. Min Act: -0.1700
Data Index: 2215277 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.5213. Min Act: -0.1700
Data Index: 343892 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.5838. Min Act: -0.1700
Data Index: 2099453 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.5213. Min Act: -0.1700
Data Index: 3610711 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.5213. Min Act: -0.1700
Data Index: 4787052 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.4588. Min Act: -0.1700
Data Index: 7365656 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.4275. Min Act: -0.1700
Data Index: 6871812 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.4588. Min Act: -0.1700
Data Index: 4280132 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0526. Min Range: -5.0526
Max Act: 4.4900. Min Act: -0.1700
Data Index: 4947963 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19