Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3593 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.4754. Min Act: -0.1700
Data Index: 380429 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.3817. Min Act: -0.1700
Data Index: 360220 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.2567. Min Act: -0.1700
Data Index: 4046100 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.2879. Min Act: -0.1700
Data Index: 5294043 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.2567. Min Act: -0.1700
Data Index: 4436645 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.2567. Min Act: -0.1700
Data Index: 3140837 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.1942. Min Act: -0.1700
Data Index: 8577915 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.2254. Min Act: -0.1700
Data Index: 8674625 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.2254. Min Act: -0.1700
Data Index: 5768458 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.2254. Min Act: -0.1700
Data Index: 950550 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.1942. Min Act: -0.1700
Data Index: 6809047 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.1317. Min Act: -0.1700
Data Index: 437408 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.1317. Min Act: -0.1700
Data Index: 8722815 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.1317. Min Act: -0.1700
Data Index: 3766377 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.1317. Min Act: -0.1700
Data Index: 5970669 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.1004. Min Act: -0.1700
Data Index: 8465257 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.1317. Min Act: -0.1700
Data Index: 734303 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.0692. Min Act: -0.1700
Data Index: 5949828 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.0692. Min Act: -0.1700
Data Index: 4216321 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4754. Min Range: -6.4754
Max Act: 6.0379. Min Act: -0.1700
Data Index: 1543542 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19