Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3834 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1804. Min Range: -5.1804
Max Act: 5.1804. Min Act: -0.1700
Data Index: 4048622 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.6179. Min Act: -0.1700
Data Index: 3246712 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.3991. Min Act: -0.1700
Data Index: 6240119 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.3053. Min Act: -0.1700
Data Index: 693654 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.2428. Min Act: -0.1700
Data Index: 2911359 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.1803. Min Act: -0.1700
Data Index: 729293 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.1803. Min Act: -0.1700
Data Index: 7050857 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.1491. Min Act: -0.1700
Data Index: 3554038 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.1178. Min Act: -0.1700
Data Index: 1942286 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.1178. Min Act: -0.1700
Data Index: 57879 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.1178. Min Act: -0.1700
Data Index: 57880 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.1178. Min Act: -0.1700
Data Index: 2970206 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.1491. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.1178. Min Act: -0.1700
Data Index: 7685412 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.0866. Min Act: -0.1700
Data Index: 1282693 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.0866. Min Act: -0.1700
Data Index: 4841583 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.1178. Min Act: -0.1700
Data Index: 6101280 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.1178. Min Act: -0.1700
Data Index: 8589134 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.1178. Min Act: -0.1700
Data Index: 3281584 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1804. Min Range: -5.1804
Max Act: 4.0866. Min Act: -0.1700
Data Index: 3389207 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19