Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7015. Min Range: -7.7015
Max Act: 7.7015. Min Act: -0.1700
Data Index: 3644361 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7015. Min Range: -7.7015
Max Act: 7.4515. Min Act: -0.1700
Data Index: 2808620 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7015. Min Range: -7.7015
Max Act: 7.4515. Min Act: -0.1700
Data Index: 3702518 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7015. Min Range: -7.7015
Max Act: 7.3890. Min Act: -0.1700
Data Index: 456517 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7015. Min Range: -7.7015
Max Act: 7.3578. Min Act: -0.1700
Data Index: 3816402 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7015. Min Range: -7.7015
Max Act: 7.3265. Min Act: -0.1700
Data Index: 315096 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7015. Min Range: -7.7015
Max Act: 7.2640. Min Act: -0.1700
Data Index: 6287537 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7015. Min Range: -7.7015
Max Act: 7.1078. Min Act: -0.1700
Data Index: 4335928 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7015. Min Range: -7.7015
Max Act: 7.0765. Min Act: -0.1700
Data Index: 4382400 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7015. Min Range: -7.7015
Max Act: 7.0140. Min Act: -0.1700
Data Index: 6011795 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7015. Min Range: -7.7015
Max Act: 6.9828. Min Act: -0.1700
Data Index: 4447212 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7015. Min Range: -7.7015
Max Act: 6.9515. Min Act: -0.1700
Data Index: 7367147 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7015. Min Range: -7.7015
Max Act: 6.9203. Min Act: -0.1700
Data Index: 2669822 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7015. Min Range: -7.7015
Max Act: 6.8890. Min Act: -0.1700
Data Index: 8165704 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7015. Min Range: -7.7015
Max Act: 6.8578. Min Act: -0.1700
Data Index: 3273816 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7015. Min Range: -7.7015
Max Act: 6.8265. Min Act: -0.1700
Data Index: 1873916 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7015. Min Range: -7.7015
Max Act: 6.8578. Min Act: -0.1700
Data Index: 1335771 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7015. Min Range: -7.7015
Max Act: 6.8265. Min Act: -0.1700
Data Index: 3314445 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7015. Min Range: -7.7015
Max Act: 6.7953. Min Act: -0.1700
Data Index: 3536744 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7015. Min Range: -7.7015
Max Act: 6.7953. Min Act: -0.1700
Data Index: 4060739 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19