Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1614 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0534. Min Range: -5.0534
Max Act: 5.0534. Min Act: -0.1700
Data Index: 2120228 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0534. Min Range: -5.0534
Max Act: 5.0534. Min Act: -0.1700
Data Index: 5791655 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0534. Min Range: -5.0534
Max Act: 5.0221. Min Act: -0.1700
Data Index: 4578103 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0534. Min Range: -5.0534
Max Act: 5.0534. Min Act: -0.1700
Data Index: 3916944 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0534. Min Range: -5.0534
Max Act: 5.0534. Min Act: -0.1700
Data Index: 8483265 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0534. Min Range: -5.0534
Max Act: 5.0221. Min Act: -0.1700
Data Index: 453628 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0534. Min Range: -5.0534
Max Act: 5.0221. Min Act: -0.1700
Data Index: 2569378 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0534. Min Range: -5.0534
Max Act: 4.9909. Min Act: -0.1700
Data Index: 8558084 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0534. Min Range: -5.0534
Max Act: 4.9909. Min Act: -0.1700
Data Index: 1938024 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0534. Min Range: -5.0534
Max Act: 4.9909. Min Act: -0.1700
Data Index: 6031886 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0534. Min Range: -5.0534
Max Act: 4.9596. Min Act: -0.1700
Data Index: 6844306 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0534. Min Range: -5.0534
Max Act: 4.9596. Min Act: -0.1700
Data Index: 8396031 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0534. Min Range: -5.0534
Max Act: 4.9596. Min Act: -0.1700
Data Index: 2816530 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0534. Min Range: -5.0534
Max Act: 4.9909. Min Act: -0.1700
Data Index: 7343490 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0534. Min Range: -5.0534
Max Act: 4.9596. Min Act: -0.1700
Data Index: 6346908 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0534. Min Range: -5.0534
Max Act: 4.9596. Min Act: -0.1700
Data Index: 4498466 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0534. Min Range: -5.0534
Max Act: 4.9596. Min Act: -0.1700
Data Index: 4973015 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0534. Min Range: -5.0534
Max Act: 4.9284. Min Act: -0.1700
Data Index: 1233628 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0534. Min Range: -5.0534
Max Act: 4.9284. Min Act: -0.1700
Data Index: 100465 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0534. Min Range: -5.0534
Max Act: 4.9284. Min Act: -0.1700
Data Index: 4551950 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19