Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5303 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.5834. Min Act: -0.1700
Data Index: 6343475 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.0834. Min Act: -0.1700
Data Index: 3783661 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.0834. Min Act: -0.1700
Data Index: 2813471 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.0209. Min Act: -0.1700
Data Index: 4981337 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9584. Min Act: -0.1700
Data Index: 1012665 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9897. Min Act: -0.1700
Data Index: 8065628 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9584. Min Act: -0.1700
Data Index: 3580682 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9584. Min Act: -0.1700
Data Index: 6931542 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9272. Min Act: -0.1700
Data Index: 6702200 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9272. Min Act: -0.1700
Data Index: 6222605 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.8959. Min Act: -0.1700
Data Index: 6686680 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.8959. Min Act: -0.1700
Data Index: 8074566 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.8647. Min Act: -0.1700
Data Index: 8314662 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.8959. Min Act: -0.1700
Data Index: 4418807 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.8334. Min Act: -0.1700
Data Index: 8603558 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.8334. Min Act: -0.1700
Data Index: 4907166 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.8334. Min Act: -0.1700
Data Index: 5518214 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.8334. Min Act: -0.1700
Data Index: 1886589 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.8021. Min Act: -0.1700
Data Index: 2134500 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.8021. Min Act: -0.1700
Data Index: 57679 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19