Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6373 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.9586. Min Act: -0.1700
Data Index: 5727758 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.9273. Min Act: -0.1700
Data Index: 1567429 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.9273. Min Act: -0.1700
Data Index: 5567041 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.8961. Min Act: -0.1700
Data Index: 5123581 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.8648. Min Act: -0.1700
Data Index: 6788012 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.8648. Min Act: -0.1700
Data Index: 2786115 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.8023. Min Act: -0.1700
Data Index: 3240014 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.8023. Min Act: -0.1700
Data Index: 8761724 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.7711. Min Act: -0.1700
Data Index: 4224205 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.7711. Min Act: -0.1700
Data Index: 6131092 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.7711. Min Act: -0.1700
Data Index: 5068491 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.7711. Min Act: -0.1700
Data Index: 6738045 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.7086. Min Act: -0.1700
Data Index: 6798197 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.6773. Min Act: -0.1700
Data Index: 179503 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.7086. Min Act: -0.1700
Data Index: 1126703 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.6773. Min Act: -0.1700
Data Index: 6131083 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.6461. Min Act: -0.1700
Data Index: 3611194 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.6773. Min Act: -0.1700
Data Index: 6142612 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.6461. Min Act: -0.1700
Data Index: 588101 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.6148. Min Act: -0.1700
Data Index: 364250 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19