Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4826 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3888. Min Range: -6.3888
Max Act: 6.3888. Min Act: -0.1700
Data Index: 2389081 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3888. Min Range: -6.3888
Max Act: 6.0763. Min Act: -0.1700
Data Index: 6559189 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3888. Min Range: -6.3888
Max Act: 6.0138. Min Act: -0.1700
Data Index: 4424272 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3888. Min Range: -6.3888
Max Act: 6.0450. Min Act: -0.1700
Data Index: 5008211 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.9513. Min Act: -0.1700
Data Index: 8790320 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.9200. Min Act: -0.1700
Data Index: 5223559 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.8888. Min Act: -0.1700
Data Index: 513337 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.8575. Min Act: -0.1700
Data Index: 5020386 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.8575. Min Act: -0.1700
Data Index: 7852696 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.8575. Min Act: -0.1700
Data Index: 2871481 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.8263. Min Act: -0.1700
Data Index: 5654789 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.8263. Min Act: -0.1700
Data Index: 5616760 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.8263. Min Act: -0.1700
Data Index: 1816583 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.8263. Min Act: -0.1700
Data Index: 2387766 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.7950. Min Act: -0.1700
Data Index: 8550423 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.7950. Min Act: -0.1700
Data Index: 6452750 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.7950. Min Act: -0.1700
Data Index: 5382114 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.7950. Min Act: -0.1700
Data Index: 4650971 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.7950. Min Act: -0.1700
Data Index: 3194393 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3888. Min Range: -6.3888
Max Act: 5.7950. Min Act: -0.1700
Data Index: 4625835 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19