Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4559 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.8545. Min Act: -0.1700
Data Index: 3110076 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7920. Min Act: -0.1700
Data Index: 6632008 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7920. Min Act: -0.1700
Data Index: 1178740 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7920. Min Act: -0.1700
Data Index: 7153729 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7920. Min Act: -0.1700
Data Index: 7072371 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7920. Min Act: -0.1700
Data Index: 6846069 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7920. Min Act: -0.1700
Data Index: 1312087 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7607. Min Act: -0.1700
Data Index: 7883261 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7607. Min Act: -0.1700
Data Index: 6327233 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7607. Min Act: -0.1700
Data Index: 6351573 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7607. Min Act: -0.1700
Data Index: 8351705 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7294. Min Act: -0.1700
Data Index: 6775049 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7607. Min Act: -0.1700
Data Index: 3543950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7607. Min Act: -0.1700
Data Index: 6220327 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7294. Min Act: -0.1700
Data Index: 119131 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7294. Min Act: -0.1700
Data Index: 5479813 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.7294. Min Act: -0.1700
Data Index: 4980052 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.6355. Min Act: -0.1700
Data Index: 4332998 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.6355. Min Act: -0.1700
Data Index: 1218646 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8545. Min Range: -3.8545
Max Act: 3.5729. Min Act: -0.1700
Data Index: 7405109 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19