Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3222. Min Range: -7.3222
Max Act: 7.3222. Min Act: -0.1700
Data Index: 790266 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3222. Min Range: -7.3222
Max Act: 7.2285. Min Act: -0.1700
Data Index: 5055251 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3222. Min Range: -7.3222
Max Act: 7.0097. Min Act: -0.1700
Data Index: 2222958 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.9472. Min Act: -0.1700
Data Index: 3438910 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.8535. Min Act: -0.1700
Data Index: 3587723 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.6035. Min Act: -0.1700
Data Index: 724354 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.5722. Min Act: -0.1700
Data Index: 733220 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.4785. Min Act: -0.1700
Data Index: 5013074 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.4785. Min Act: -0.1700
Data Index: 5121410 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.4785. Min Act: -0.1700
Data Index: 4237435 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.5097. Min Act: -0.1700
Data Index: 648249 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.4472. Min Act: -0.1700
Data Index: 4029105 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.3847. Min Act: -0.1700
Data Index: 4601726 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.4160. Min Act: -0.1700
Data Index: 8654284 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.3535. Min Act: -0.1700
Data Index: 8613693 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.3535. Min Act: -0.1700
Data Index: 4916669 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.3535. Min Act: -0.1700
Data Index: 3041405 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.3222. Min Act: -0.1700
Data Index: 3510840 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.3535. Min Act: -0.1700
Data Index: 8271011 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3222. Min Range: -7.3222
Max Act: 6.3222. Min Act: -0.1700
Data Index: 7982442 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19