Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3991 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.9764. Min Act: -0.1700
Data Index: 5348610 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.9139. Min Act: -0.1700
Data Index: 3671390 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.8827. Min Act: -0.1700
Data Index: 378796 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.7577. Min Act: -0.1700
Data Index: 8407834 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.7577. Min Act: -0.1700
Data Index: 1837429 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.7577. Min Act: -0.1700
Data Index: 7271877 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.7264. Min Act: -0.1700
Data Index: 3531118 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.7577. Min Act: -0.1700
Data Index: 558101 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.6952. Min Act: -0.1700
Data Index: 5811749 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.6952. Min Act: -0.1700
Data Index: 2146552 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.6639. Min Act: -0.1700
Data Index: 8065831 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.6639. Min Act: -0.1700
Data Index: 75543 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.6014. Min Act: -0.1700
Data Index: 4891169 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.6327. Min Act: -0.1700
Data Index: 3725407 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.6327. Min Act: -0.1700
Data Index: 388482 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.6327. Min Act: -0.1700
Data Index: 4900300 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.6327. Min Act: -0.1700
Data Index: 4042759 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.6014. Min Act: -0.1700
Data Index: 8676373 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.5702. Min Act: -0.1700
Data Index: 7882707 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9764. Min Range: -6.9764
Max Act: 6.5702. Min Act: -0.1700
Data Index: 6282688 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19