Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1062 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0933. Min Range: -4.0933
Max Act: 4.0933. Min Act: -0.1700
Data Index: 2124235 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0933. Min Range: -4.0933
Max Act: 4.0620. Min Act: -0.1700
Data Index: 1347227 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9995. Min Act: -0.1700
Data Index: 4056603 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0933. Min Range: -4.0933
Max Act: 4.0308. Min Act: -0.1700
Data Index: 6838701 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0933. Min Range: -4.0933
Max Act: 4.0308. Min Act: -0.1700
Data Index: 7743807 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9682. Min Act: -0.1700
Data Index: 5376261 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9995. Min Act: -0.1700
Data Index: 3365928 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9995. Min Act: -0.1700
Data Index: 8454977 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9682. Min Act: -0.1700
Data Index: 7007712 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9370. Min Act: -0.1700
Data Index: 3149918 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9682. Min Act: -0.1700
Data Index: 8248318 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9682. Min Act: -0.1700
Data Index: 5055627 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9682. Min Act: -0.1700
Data Index: 1682395 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9682. Min Act: -0.1700
Data Index: 32775 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9370. Min Act: -0.1700
Data Index: 4560491 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9370. Min Act: -0.1700
Data Index: 4120086 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9370. Min Act: -0.1700
Data Index: 518423 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9370. Min Act: -0.1700
Data Index: 7911550 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9370. Min Act: -0.1700
Data Index: 1329783 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0933. Min Range: -4.0933
Max Act: 3.9057. Min Act: -0.1700
Data Index: 6256784 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19