Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2896 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0412. Min Range: -9.0412
Max Act: 9.0412. Min Act: -0.1700
Data Index: 7002391 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.9162. Min Act: -0.1700
Data Index: 1568277 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.9162. Min Act: -0.1700
Data Index: 621529 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.7287. Min Act: -0.1700
Data Index: 4100388 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.6037. Min Act: -0.1700
Data Index: 911845 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.4787. Min Act: -0.1700
Data Index: 4661339 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.4787. Min Act: -0.1700
Data Index: 6067419 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.4787. Min Act: -0.1700
Data Index: 8401604 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.4162. Min Act: -0.1700
Data Index: 5587754 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.4162. Min Act: -0.1700
Data Index: 8478121 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.4162. Min Act: -0.1700
Data Index: 1889559 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.3537. Min Act: -0.1700
Data Index: 4994429 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.3537. Min Act: -0.1700
Data Index: 2113862 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.2912. Min Act: -0.1700
Data Index: 6621119 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.2912. Min Act: -0.1700
Data Index: 2228554 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.2912. Min Act: -0.1700
Data Index: 6267522 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.2912. Min Act: -0.1700
Data Index: 5899861 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.1662. Min Act: -0.1700
Data Index: 1746336 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.2287. Min Act: -0.1700
Data Index: 1436262 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0412. Min Range: -9.0412
Max Act: 8.2287. Min Act: -0.1700
Data Index: 3138223 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19