Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5422 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.7689. Min Act: -0.1700
Data Index: 5998570 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.7370. Min Act: -0.1700
Data Index: 7779019 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.7210. Min Act: -0.1700
Data Index: 4533012 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.7050. Min Act: -0.1700
Data Index: 1147788 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6570. Min Act: -0.1700
Data Index: 8285205 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6570. Min Act: -0.1700
Data Index: 3701714 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6570. Min Act: -0.1700
Data Index: 1555566 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6570. Min Act: -0.1700
Data Index: 1984936 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6249. Min Act: -0.1700
Data Index: 2256487 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6570. Min Act: -0.1700
Data Index: 8579582 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6088. Min Act: -0.1700
Data Index: 2074238 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6249. Min Act: -0.1700
Data Index: 352260 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6088. Min Act: -0.1700
Data Index: 3151548 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6088. Min Act: -0.1700
Data Index: 3253979 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6088. Min Act: -0.1700
Data Index: 377422 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6088. Min Act: -0.1700
Data Index: 1588533 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6088. Min Act: -0.1700
Data Index: 1296570 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6249. Min Act: -0.1700
Data Index: 7921825 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.6088. Min Act: -0.1700
Data Index: 1392152 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7689. Min Range: -2.7689
Max Act: 2.5766. Min Act: -0.1700
Data Index: 2607219 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19