Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.6185. Min Act: -0.1700
Data Index: 3429781 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.5873. Min Act: -0.1700
Data Index: 363686 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.5560. Min Act: -0.1700
Data Index: 4045751 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.5560. Min Act: -0.1700
Data Index: 481952 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4935. Min Act: -0.1700
Data Index: 4419969 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4935. Min Act: -0.1698
Data Index: 5652031 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4623. Min Act: -0.1700
Data Index: 1606135 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4935. Min Act: -0.1700
Data Index: 4567765 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4935. Min Act: -0.1696
Data Index: 4397884 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4935. Min Act: -0.1700
Data Index: 2761181 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4623. Min Act: -0.1700
Data Index: 3956890 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4623. Min Act: -0.1700
Data Index: 5861899 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4310. Min Act: -0.1700
Data Index: 898362 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4310. Min Act: -0.1700
Data Index: 6780665 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4310. Min Act: -0.1700
Data Index: 1595619 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4310. Min Act: -0.1700
Data Index: 5260034 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4310. Min Act: -0.1699
Data Index: 5325200 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4623. Min Act: -0.1699
Data Index: 1913462 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4310. Min Act: -0.1700
Data Index: 2112163 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6185. Min Range: -5.6185
Max Act: 5.4310. Min Act: -0.1700
Data Index: 3616638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19