Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.8535. Min Act: -0.1700
Data Index: 89486 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.7910. Min Act: -0.1700
Data Index: 6286440 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.7285. Min Act: -0.1700
Data Index: 7779470 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.7285. Min Act: -0.1700
Data Index: 7953763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.7285. Min Act: -0.1700
Data Index: 4461028 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.7285. Min Act: -0.1700
Data Index: 3879876 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.7285. Min Act: -0.1698
Data Index: 33977 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.6660. Min Act: -0.1700
Data Index: 79633 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.6660. Min Act: -0.1700
Data Index: 1137517 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.6660. Min Act: -0.1697
Data Index: 3506327 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.6660. Min Act: -0.1694
Data Index: 726170 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.6660. Min Act: -0.1700
Data Index: 3392113 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.6660. Min Act: -0.1700
Data Index: 2903827 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.6660. Min Act: -0.1678
Data Index: 426230 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.6660. Min Act: -0.1700
Data Index: 2310862 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.6660. Min Act: -0.1695
Data Index: 3126280 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.6660. Min Act: -0.1700
Data Index: 1025057 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.6660. Min Act: -0.1697
Data Index: 2152138 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.6660. Min Act: -0.1700
Data Index: 1948409 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8535. Min Range: -6.8535
Max Act: 6.6660. Min Act: -0.1700
Data Index: 411397 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19