Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 895 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2765. Min Range: -2.2765
Max Act: 2.2765. Min Act: -0.1700
Data Index: 2688794 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2765. Min Range: -2.2765
Max Act: 2.0602. Min Act: -0.1700
Data Index: 8479408 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2765. Min Range: -2.2765
Max Act: 2.0433. Min Act: -0.1700
Data Index: 3354936 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2765. Min Range: -2.2765
Max Act: 2.0096. Min Act: -0.1700
Data Index: 7497255 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9927. Min Act: -0.1700
Data Index: 5186200 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9927. Min Act: -0.1700
Data Index: 6180898 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9758. Min Act: -0.1700
Data Index: 8404640 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9504. Min Act: -0.1700
Data Index: 197365 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9504. Min Act: -0.1700
Data Index: 8089781 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9588. Min Act: -0.1700
Data Index: 420119 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9419. Min Act: -0.1700
Data Index: 6232370 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9419. Min Act: -0.1700
Data Index: 3718226 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9334. Min Act: -0.1700
Data Index: 5844957 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9334. Min Act: -0.1700
Data Index: 2672911 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9249. Min Act: -0.1700
Data Index: 8120118 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9164. Min Act: -0.1700
Data Index: 4420660 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9249. Min Act: -0.1700
Data Index: 4794305 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.9334. Min Act: -0.1700
Data Index: 7322930 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.8993. Min Act: -0.1700
Data Index: 2688796 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2765. Min Range: -2.2765
Max Act: 1.8993. Min Act: -0.1700
Data Index: 2035582 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19