Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6391 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3717. Min Range: -8.3717
Max Act: 8.3717. Min Act: -0.1700
Data Index: 3173487 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3717. Min Range: -8.3717
Max Act: 8.2467. Min Act: -0.1700
Data Index: 8349673 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3717. Min Range: -8.3717
Max Act: 8.1217. Min Act: -0.1700
Data Index: 8349669 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3717. Min Range: -8.3717
Max Act: 8.1217. Min Act: -0.1700
Data Index: 5760358 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3717. Min Range: -8.3717
Max Act: 8.1217. Min Act: -0.1700
Data Index: 8349650 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.9967. Min Act: -0.1700
Data Index: 6520014 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.9342. Min Act: -0.1700
Data Index: 8349652 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.9342. Min Act: -0.1700
Data Index: 8349664 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.9342. Min Act: -0.1700
Data Index: 8349654 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.9342. Min Act: -0.1700
Data Index: 8349656 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.8092. Min Act: -0.1700
Data Index: 8349661 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.6529. Min Act: -0.1700
Data Index: 8349666 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.5904. Min Act: -0.1700
Data Index: 8349663 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.5904. Min Act: -0.1700
Data Index: 728795 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.5592. Min Act: -0.1700
Data Index: 191301 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.5904. Min Act: -0.1700
Data Index: 8349653 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.5279. Min Act: -0.1699
Data Index: 8349651 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.4967. Min Act: -0.1700
Data Index: 8349659 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.4654. Min Act: -0.1700
Data Index: 1179385 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3717. Min Range: -8.3717
Max Act: 7.4029. Min Act: -0.1700
Data Index: 6162937 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19