Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2152 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.6707. Min Act: -0.1700
Data Index: 4335702 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.6707. Min Act: -0.1700
Data Index: 8578968 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.6395. Min Act: -0.1700
Data Index: 8578032 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.6082. Min Act: -0.1700
Data Index: 6705340 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.6082. Min Act: -0.1700
Data Index: 2166031 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.5770. Min Act: -0.1700
Data Index: 3431577 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.5770. Min Act: -0.1700
Data Index: 2313524 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.5145. Min Act: -0.1700
Data Index: 4848857 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.5145. Min Act: -0.1700
Data Index: 3549078 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4832. Min Act: -0.1700
Data Index: 1979844 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4832. Min Act: -0.1700
Data Index: 460424 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4832. Min Act: -0.1700
Data Index: 2973047 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4207. Min Act: -0.1700
Data Index: 1657593 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4520. Min Act: -0.1700
Data Index: 4059113 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4520. Min Act: -0.1700
Data Index: 3369454 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4207. Min Act: -0.1700
Data Index: 2015339 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4207. Min Act: -0.1700
Data Index: 4368293 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4207. Min Act: -0.1700
Data Index: 2393339 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4207. Min Act: -0.1700
Data Index: 6282502 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4207. Min Act: -0.1700
Data Index: 7664902 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19