Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2790 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.9850. Min Act: -0.1700
Data Index: 4247971 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.8912. Min Act: -0.1700
Data Index: 2472502 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.7662. Min Act: -0.1700
Data Index: 100164 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.4850. Min Act: -0.1700
Data Index: 4686101 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.5162. Min Act: -0.1700
Data Index: 6101526 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.4225. Min Act: -0.1700
Data Index: 4334342 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.4537. Min Act: -0.1700
Data Index: 1554252 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.3912. Min Act: -0.1700
Data Index: 3095947 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.4225. Min Act: -0.1700
Data Index: 3008190 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.3912. Min Act: -0.1700
Data Index: 7714083 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.3912. Min Act: -0.1700
Data Index: 83740 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.3912. Min Act: -0.1700
Data Index: 5062529 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.3600. Min Act: -0.1700
Data Index: 5470695 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.3287. Min Act: -0.1700
Data Index: 2886257 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.3287. Min Act: -0.1700
Data Index: 4380089 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.3287. Min Act: -0.1700
Data Index: 3123490 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.2975. Min Act: -0.1700
Data Index: 5884969 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.2662. Min Act: -0.1700
Data Index: 5246909 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.2975. Min Act: -0.1700
Data Index: 3810714 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9850. Min Range: -6.9850
Max Act: 6.1725. Min Act: -0.1700
Data Index: 7493886 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19