Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1095 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.8809. Min Act: -0.1700
Data Index: 3788024 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.8333. Min Act: -0.1700
Data Index: 794457 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.7696. Min Act: -0.1700
Data Index: 3607850 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.7536. Min Act: -0.1700
Data Index: 2294522 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.7217. Min Act: -0.1700
Data Index: 3788022 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.7217. Min Act: -0.1700
Data Index: 2994996 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.7057. Min Act: -0.1700
Data Index: 406199 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.7057. Min Act: -0.1700
Data Index: 3700715 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.7057. Min Act: -0.1700
Data Index: 2624787 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.7057. Min Act: -0.1700
Data Index: 3213389 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.6897. Min Act: -0.1700
Data Index: 3800268 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.6897. Min Act: -0.1700
Data Index: 406617 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.6737. Min Act: -0.1700
Data Index: 6233660 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.6737. Min Act: -0.1700
Data Index: 5700183 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.6737. Min Act: -0.1700
Data Index: 3696747 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.6576. Min Act: -0.1700
Data Index: 8101472 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.6416. Min Act: -0.1700
Data Index: 1125503 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.6416. Min Act: -0.1700
Data Index: 3362026 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.6416. Min Act: -0.1700
Data Index: 763506 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8809. Min Range: -2.8809
Max Act: 2.6416. Min Act: -0.1700
Data Index: 6856266 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19