Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.5264. Min Act: -0.1700
Data Index: 6509623 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.4639. Min Act: -0.1700
Data Index: 4825565 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.4014. Min Act: -0.1700
Data Index: 3687563 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.3389. Min Act: -0.1700
Data Index: 1462390 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.3389. Min Act: -0.1700
Data Index: 3142496 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.2764. Min Act: -0.1700
Data Index: 7914004 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.2139. Min Act: -0.1700
Data Index: 8459974 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.2139. Min Act: -0.1700
Data Index: 8799878 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.2139. Min Act: -0.1700
Data Index: 4456623 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.2139. Min Act: -0.1700
Data Index: 5178551 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.0889. Min Act: -0.1700
Data Index: 5697728 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.0889. Min Act: -0.1700
Data Index: 2551201 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.0889. Min Act: -0.1700
Data Index: 1517752 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.0264. Min Act: -0.1700
Data Index: 4825559 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5264. Min Range: -9.5264
Max Act: 8.9639. Min Act: -0.1700
Data Index: 7307526 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5264. Min Range: -9.5264
Max Act: 9.0264. Min Act: -0.1700
Data Index: 1221285 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5264. Min Range: -9.5264
Max Act: 8.9639. Min Act: -0.1700
Data Index: 4901084 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5264. Min Range: -9.5264
Max Act: 8.9639. Min Act: -0.1700
Data Index: 197982 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5264. Min Range: -9.5264
Max Act: 8.9014. Min Act: -0.1700
Data Index: 3547259 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5264. Min Range: -9.5264
Max Act: 8.9639. Min Act: -0.1700
Data Index: 2041703 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19