Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.8662. Min Act: -0.1700
Data Index: 8260279 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.8505. Min Act: -0.1700
Data Index: 8766605 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.8505. Min Act: -0.1700
Data Index: 8238024 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.7567. Min Act: -0.1700
Data Index: 5565472 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.6785. Min Act: -0.1700
Data Index: 2049789 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.6315. Min Act: -0.1700
Data Index: 78722 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.6002. Min Act: -0.1700
Data Index: 475502 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.6159. Min Act: -0.1700
Data Index: 254260 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.6002. Min Act: -0.1700
Data Index: 7342895 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.6159. Min Act: -0.1700
Data Index: 4190145 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.6002. Min Act: -0.1700
Data Index: 7545845 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.6002. Min Act: -0.1700
Data Index: 2935383 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.5689. Min Act: -0.1700
Data Index: 2635830 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.5533. Min Act: -0.1700
Data Index: 4714581 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.5533. Min Act: -0.1700
Data Index: 6809230 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.5533. Min Act: -0.1700
Data Index: 4227880 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.5376. Min Act: -0.1700
Data Index: 2333693 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.5376. Min Act: -0.1700
Data Index: 3754247 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.5220. Min Act: -0.1700
Data Index: 1610097 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8662. Min Range: -3.8662
Max Act: 3.5220. Min Act: -0.1700
Data Index: 6673414 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19