Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5310 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.2613. Min Act: -0.1700
Data Index: 386717 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.1988. Min Act: -0.1700
Data Index: 4029237 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.1676. Min Act: -0.1700
Data Index: 342321 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.1676. Min Act: -0.1700
Data Index: 8394411 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.1363. Min Act: -0.1700
Data Index: 7796012 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.1363. Min Act: -0.1700
Data Index: 4025130 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.1363. Min Act: -0.1700
Data Index: 8140262 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.1363. Min Act: -0.1700
Data Index: 4944077 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.1051. Min Act: -0.1700
Data Index: 7716572 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.1051. Min Act: -0.1700
Data Index: 1994295 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.1051. Min Act: -0.1700
Data Index: 3779358 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.1051. Min Act: -0.1700
Data Index: 8040621 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.1051. Min Act: -0.1700
Data Index: 8453767 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.1051. Min Act: -0.1700
Data Index: 4586270 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.0738. Min Act: -0.1700
Data Index: 7241797 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.0738. Min Act: -0.1700
Data Index: 589126 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.0738. Min Act: -0.1700
Data Index: 6514720 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.0738. Min Act: -0.1700
Data Index: 6472794 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.0426. Min Act: -0.1700
Data Index: 7971693 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2613. Min Range: -6.2613
Max Act: 6.0738. Min Act: -0.1700
Data Index: 8198962 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19