Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1247 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.6086. Min Act: -0.1700
Data Index: 4373081 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.6086. Min Act: -0.1700
Data Index: 707041 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.6086. Min Act: -0.1700
Data Index: 3538210 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.6086. Min Act: -0.1700
Data Index: 5423593 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.5460. Min Act: -0.1700
Data Index: 2600996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.5147. Min Act: -0.1700
Data Index: 6450263 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.5147. Min Act: -0.1700
Data Index: 3910323 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.5147. Min Act: -0.1700
Data Index: 810533 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.5147. Min Act: -0.1700
Data Index: 8344891 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.4833. Min Act: -0.1700
Data Index: 3537949 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.4833. Min Act: -0.1700
Data Index: 3457302 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.4833. Min Act: -0.1700
Data Index: 6000668 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.4833. Min Act: -0.1700
Data Index: 1391644 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.4833. Min Act: -0.1700
Data Index: 5251784 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.4833. Min Act: -0.1700
Data Index: 2175750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.4833. Min Act: -0.1700
Data Index: 337933 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.4833. Min Act: -0.1700
Data Index: 7660750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.4520. Min Act: -0.1700
Data Index: 5651014 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.4520. Min Act: -0.1700
Data Index: 6203074 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6086. Min Range: -3.6086
Max Act: 3.4520. Min Act: -0.1700
Data Index: 6436794 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19