Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 96 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.5901. Min Act: -0.1700
Data Index: 8430579 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.4651. Min Act: -0.1700
Data Index: 8477563 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.3401. Min Act: -0.1700
Data Index: 1080903 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.3088. Min Act: -0.1700
Data Index: 5992311 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.2463. Min Act: -0.1700
Data Index: 3043204 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.2463. Min Act: -0.1700
Data Index: 6821038 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.2463. Min Act: -0.1700
Data Index: 7741328 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.1838. Min Act: -0.1700
Data Index: 4648240 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.1838. Min Act: -0.1700
Data Index: 25146 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.1838. Min Act: -0.1700
Data Index: 6881007 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.1525. Min Act: -0.1700
Data Index: 7404201 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.1525. Min Act: -0.1700
Data Index: 4485848 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.1525. Min Act: -0.1700
Data Index: 6760677 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.1525. Min Act: -0.1700
Data Index: 947626 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.1213. Min Act: -0.1700
Data Index: 4222997 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.1213. Min Act: -0.1700
Data Index: 3129682 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.1213. Min Act: -0.1700
Data Index: 4316527 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.0900. Min Act: -0.1700
Data Index: 1613340 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.1213. Min Act: -0.1700
Data Index: 3944779 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5901. Min Range: -4.5901
Max Act: 4.1213. Min Act: -0.1700
Data Index: 4202526 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19