Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.4200. Min Act: -0.1700
Data Index: 4709181 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.3575. Min Act: -0.1700
Data Index: 6223924 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2638. Min Act: -0.1700
Data Index: 4914008 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2013. Min Act: -0.1700
Data Index: 2505704 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2013. Min Act: -0.1700
Data Index: 7757795 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2013. Min Act: -0.1700
Data Index: 3866048 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.1700. Min Act: -0.1700
Data Index: 2789352 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.1700. Min Act: -0.1700
Data Index: 6470380 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.1700. Min Act: -0.1700
Data Index: 6668319 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.1388. Min Act: -0.1700
Data Index: 1147838 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.1075. Min Act: -0.1700
Data Index: 8216660 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.1075. Min Act: -0.1700
Data Index: 5692708 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.0763. Min Act: -0.1700
Data Index: 2075741 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.1075. Min Act: -0.1700
Data Index: 5553459 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.1075. Min Act: -0.1700
Data Index: 7092515 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.1075. Min Act: -0.1700
Data Index: 1820901 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.1075. Min Act: -0.1700
Data Index: 7881951 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.0763. Min Act: -0.1700
Data Index: 7646383 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.0763. Min Act: -0.1700
Data Index: 6063644 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.0763. Min Act: -0.1700
Data Index: 3116422 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19