Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5079 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.7039. Min Act: -0.1700
Data Index: 1362920 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.7039. Min Act: -0.1700
Data Index: 4096299 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.7039. Min Act: -0.1700
Data Index: 5926966 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.6726. Min Act: -0.1700
Data Index: 2087357 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.6726. Min Act: -0.1700
Data Index: 5268758 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.6414. Min Act: -0.1700
Data Index: 3862356 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.6414. Min Act: -0.1700
Data Index: 808437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.6414. Min Act: -0.1700
Data Index: 5349783 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.6101. Min Act: -0.1700
Data Index: 7766793 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.6101. Min Act: -0.1700
Data Index: 97676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.6101. Min Act: -0.1700
Data Index: 4525907 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.6101. Min Act: -0.1699
Data Index: 8562047 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.5789. Min Act: -0.1700
Data Index: 3661256 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.5789. Min Act: -0.1700
Data Index: 6532112 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.5789. Min Act: -0.1688
Data Index: 552877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.3601. Min Act: -0.1700
Data Index: 6129638 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.3601. Min Act: -0.1700
Data Index: 2085924 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.3289. Min Act: -0.1700
Data Index: 6075286 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.3289. Min Act: -0.1700
Data Index: 7143376 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7039. Min Range: -5.7039
Max Act: 5.3289. Min Act: -0.1700
Data Index: 7632006 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19