Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3417 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.9898. Min Act: -0.1700
Data Index: 5398712 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.9585. Min Act: -0.1700
Data Index: 1093855 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.9585. Min Act: -0.1700
Data Index: 401350 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.9585. Min Act: -0.1700
Data Index: 3403621 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.9273. Min Act: -0.1700
Data Index: 7250024 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.8960. Min Act: -0.1700
Data Index: 6653688 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.8648. Min Act: -0.1700
Data Index: 4972114 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.8648. Min Act: -0.1700
Data Index: 7386387 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.8648. Min Act: -0.1700
Data Index: 7001026 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.8335. Min Act: -0.1700
Data Index: 6469317 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.8335. Min Act: -0.1700
Data Index: 3546678 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.8023. Min Act: -0.1700
Data Index: 7262818 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.8023. Min Act: -0.1700
Data Index: 1814412 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.7710. Min Act: -0.1700
Data Index: 7308436 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.7710. Min Act: -0.1700
Data Index: 497092 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.8023. Min Act: -0.1700
Data Index: 2193231 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.7398. Min Act: -0.1700
Data Index: 6142398 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.7398. Min Act: -0.1700
Data Index: 3228498 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.7398. Min Act: -0.1700
Data Index: 7137475 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.7398. Min Act: -0.1700
Data Index: 3076563 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19