Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1805 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.8708. Min Act: -0.1700
Data Index: 3988205 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.7771. Min Act: -0.1700
Data Index: 5726724 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.6208. Min Act: -0.1700
Data Index: 2183195 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.5583. Min Act: -0.1700
Data Index: 999388 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.5583. Min Act: -0.1700
Data Index: 7568529 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.5271. Min Act: -0.1700
Data Index: 6719342 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.5271. Min Act: -0.1700
Data Index: 5471686 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.5271. Min Act: -0.1700
Data Index: 5782732 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.5271. Min Act: -0.1700
Data Index: 4908039 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4958. Min Act: -0.1700
Data Index: 2563375 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4958. Min Act: -0.1700
Data Index: 4876627 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4958. Min Act: -0.1700
Data Index: 7874621 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4646. Min Act: -0.1700
Data Index: 4741255 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4646. Min Act: -0.1700
Data Index: 1622337 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4333. Min Act: -0.1700
Data Index: 3241343 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4333. Min Act: -0.1700
Data Index: 7185419 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4333. Min Act: -0.1700
Data Index: 6375984 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4646. Min Act: -0.1700
Data Index: 2867718 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4021. Min Act: -0.1700
Data Index: 5996788 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4333. Min Act: -0.1700
Data Index: 6596088 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19