Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 328 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.2972. Min Act: -0.1700
Data Index: 8561083 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.2035. Min Act: -0.1700
Data Index: 890327 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.1722. Min Act: -0.1700
Data Index: 5315660 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.1410. Min Act: -0.1700
Data Index: 8255758 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.1097. Min Act: -0.1700
Data Index: 4610416 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0785. Min Act: -0.1700
Data Index: 4529440 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0785. Min Act: -0.1700
Data Index: 7567654 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0785. Min Act: -0.1698
Data Index: 6514988 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0785. Min Act: -0.1700
Data Index: 1005529 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0472. Min Act: -0.1700
Data Index: 5398422 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0472. Min Act: -0.1700
Data Index: 5373193 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0472. Min Act: -0.1700
Data Index: 2591720 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0472. Min Act: -0.1698
Data Index: 2435438 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0472. Min Act: -0.1700
Data Index: 5896226 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0472. Min Act: -0.1687
Data Index: 2006900 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0160. Min Act: -0.1700
Data Index: 225351 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0472. Min Act: -0.1686
Data Index: 3828482 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0472. Min Act: -0.1700
Data Index: 3803526 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0472. Min Act: -0.1700
Data Index: 1792792 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2972. Min Range: -5.2972
Max Act: 5.0472. Min Act: -0.1700
Data Index: 1670046 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19