Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3351 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0662. Min Range: -6.0662
Max Act: 6.0662. Min Act: -0.1700
Data Index: 5186845 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0662. Min Range: -6.0662
Max Act: 6.0349. Min Act: -0.1700
Data Index: 6716437 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0662. Min Range: -6.0662
Max Act: 6.0037. Min Act: -0.1700
Data Index: 5010205 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.9724. Min Act: -0.1700
Data Index: 5735391 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.9412. Min Act: -0.1700
Data Index: 80034 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.9412. Min Act: -0.1700
Data Index: 2275662 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.9099. Min Act: -0.1700
Data Index: 2713286 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.9099. Min Act: -0.1700
Data Index: 8148129 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.9099. Min Act: -0.1700
Data Index: 4999301 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.8787. Min Act: -0.1700
Data Index: 316068 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.8474. Min Act: -0.1700
Data Index: 4901039 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.8787. Min Act: -0.1700
Data Index: 3163024 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.8162. Min Act: -0.1700
Data Index: 4873952 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.8162. Min Act: -0.1700
Data Index: 7941593 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.8162. Min Act: -0.1700
Data Index: 6892883 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.7537. Min Act: -0.1700
Data Index: 1274133 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.7537. Min Act: -0.1700
Data Index: 2226074 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.7224. Min Act: -0.1700
Data Index: 2773171 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.7224. Min Act: -0.1700
Data Index: 3541277 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0662. Min Range: -6.0662
Max Act: 5.6912. Min Act: -0.1700
Data Index: 7755204 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19