Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4355 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0351. Min Range: -8.0351
Max Act: 8.0351. Min Act: -0.1700
Data Index: 1357912 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0351. Min Range: -8.0351
Max Act: 8.0351. Min Act: -0.1700
Data Index: 3256616 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.9413. Min Act: -0.1700
Data Index: 4225960 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.9101. Min Act: -0.1700
Data Index: 8775736 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.8788. Min Act: -0.1700
Data Index: 3320188 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.8476. Min Act: -0.1700
Data Index: 7276130 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.7851. Min Act: -0.1700
Data Index: 4153956 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.8163. Min Act: -0.1700
Data Index: 462183 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.8163. Min Act: -0.1700
Data Index: 3345303 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.8163. Min Act: -0.1700
Data Index: 1984267 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.7538. Min Act: -0.1700
Data Index: 6862780 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.7226. Min Act: -0.1700
Data Index: 4681269 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.6913. Min Act: -0.1700
Data Index: 4535927 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.6601. Min Act: -0.1700
Data Index: 4678572 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.6601. Min Act: -0.1700
Data Index: 5073189 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.6601. Min Act: -0.1700
Data Index: 953790 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.6288. Min Act: -0.1700
Data Index: 6862781 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.6288. Min Act: -0.1700
Data Index: 7776830 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.6601. Min Act: -0.1700
Data Index: 4678573 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.5663. Min Act: -0.1700
Data Index: 8091623 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19