Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.7809. Min Act: -0.1700
Data Index: 2698917 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.7809. Min Act: -0.1700
Data Index: 5946851 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.7183. Min Act: -0.1700
Data Index: 6573423 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.6088. Min Act: -0.1700
Data Index: 7594695 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.6245. Min Act: -0.1700
Data Index: 2728683 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.6558. Min Act: -0.1700
Data Index: 2891705 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.6245. Min Act: -0.1700
Data Index: 8260601 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.5932. Min Act: -0.1700
Data Index: 7801280 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.5775. Min Act: -0.1700
Data Index: 54167 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.5775. Min Act: -0.1700
Data Index: 3509751 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.5305. Min Act: -0.1700
Data Index: 2208709 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.5775. Min Act: -0.1700
Data Index: 461330 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.5775. Min Act: -0.1700
Data Index: 3014948 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.5775. Min Act: -0.1700
Data Index: 346563 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.5462. Min Act: -0.1700
Data Index: 5633372 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.5462. Min Act: -0.1700
Data Index: 4183131 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.5462. Min Act: -0.1700
Data Index: 2777182 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.4992. Min Act: -0.1700
Data Index: 3835428 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.4992. Min Act: -0.1700
Data Index: 5236612 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7809. Min Range: -3.7809
Max Act: 3.4992. Min Act: -0.1700
Data Index: 7072654 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19