Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4222 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1701. Min Range: -5.1701
Max Act: 5.1701. Min Act: -0.1700
Data Index: 1948632 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1701. Min Range: -5.1701
Max Act: 5.1076. Min Act: -0.1700
Data Index: 3826671 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1701. Min Range: -5.1701
Max Act: 5.0763. Min Act: -0.1700
Data Index: 8081699 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1701. Min Range: -5.1701
Max Act: 5.0451. Min Act: -0.1700
Data Index: 8510804 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.9826. Min Act: -0.1700
Data Index: 3872025 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.9201. Min Act: -0.1700
Data Index: 6744284 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.9513. Min Act: -0.1700
Data Index: 5410018 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.9201. Min Act: -0.1700
Data Index: 2027569 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.8888. Min Act: -0.1700
Data Index: 4839468 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.8888. Min Act: -0.1700
Data Index: 1392259 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.8576. Min Act: -0.1700
Data Index: 8360470 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.8576. Min Act: -0.1700
Data Index: 5806133 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.7951. Min Act: -0.1700
Data Index: 3028890 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.7638. Min Act: -0.1700
Data Index: 778000 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.7638. Min Act: -0.1700
Data Index: 1452221 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.7638. Min Act: -0.1700
Data Index: 5450353 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.7326. Min Act: -0.1700
Data Index: 6478294 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.7638. Min Act: -0.1700
Data Index: 8025314 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.7638. Min Act: -0.1700
Data Index: 8500382 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1701. Min Range: -5.1701
Max Act: 4.7638. Min Act: -0.1700
Data Index: 6087423 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19