Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3981 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0716. Min Range: -3.0716
Max Act: 3.0716. Min Act: -0.1700
Data Index: 4208756 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0716. Min Range: -3.0716
Max Act: 3.0401. Min Act: -0.1700
Data Index: 4841710 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0716. Min Range: -3.0716
Max Act: 3.0401. Min Act: -0.1700
Data Index: 4617000 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0716. Min Range: -3.0716
Max Act: 3.0401. Min Act: -0.1700
Data Index: 791688 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0716. Min Range: -3.0716
Max Act: 3.0401. Min Act: -0.1700
Data Index: 7706698 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0716. Min Range: -3.0716
Max Act: 3.0401. Min Act: -0.1700
Data Index: 2166636 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0716. Min Range: -3.0716
Max Act: 3.0243. Min Act: -0.1700
Data Index: 5888452 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0716. Min Range: -3.0716
Max Act: 2.9927. Min Act: -0.1700
Data Index: 7655319 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0716. Min Range: -3.0716
Max Act: 2.9768. Min Act: -0.1700
Data Index: 7476708 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0716. Min Range: -3.0716
Max Act: 2.9768. Min Act: -0.1700
Data Index: 8761289 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0716. Min Range: -3.0716
Max Act: 2.9768. Min Act: -0.1700
Data Index: 6896912 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0716. Min Range: -3.0716
Max Act: 2.9768. Min Act: -0.1700
Data Index: 6982997 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0716. Min Range: -3.0716
Max Act: 2.9452. Min Act: -0.1700
Data Index: 3424634 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0716. Min Range: -3.0716
Max Act: 2.9610. Min Act: -0.1700
Data Index: 3196723 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0716. Min Range: -3.0716
Max Act: 2.9610. Min Act: -0.1700
Data Index: 6332057 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0716. Min Range: -3.0716
Max Act: 2.9452. Min Act: -0.1700
Data Index: 5291953 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0716. Min Range: -3.0716
Max Act: 2.9294. Min Act: -0.1700
Data Index: 7822828 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0716. Min Range: -3.0716
Max Act: 2.9294. Min Act: -0.1700
Data Index: 926620 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0716. Min Range: -3.0716
Max Act: 2.9452. Min Act: -0.1700
Data Index: 5998472 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0716. Min Range: -3.0716
Max Act: 2.9452. Min Act: -0.1700
Data Index: 948289 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19