Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3689 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0582. Min Range: -2.0582
Max Act: 2.0582. Min Act: -0.1700
Data Index: 6544650 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0582. Min Range: -2.0582
Max Act: 2.0582. Min Act: -0.1693
Data Index: 805460 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9992. Min Act: -0.1700
Data Index: 3380465 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9992. Min Act: -0.1700
Data Index: 764689 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9908. Min Act: -0.1700
Data Index: 5725966 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9738. Min Act: -0.1700
Data Index: 2499060 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9569. Min Act: -0.1700
Data Index: 1930558 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9654. Min Act: -0.1700
Data Index: 2041648 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9484. Min Act: -0.1700
Data Index: 4686401 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9654. Min Act: -0.1700
Data Index: 5575742 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9399. Min Act: -0.1700
Data Index: 2202517 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9484. Min Act: -0.1700
Data Index: 4953741 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9314. Min Act: -0.1700
Data Index: 7024010 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9314. Min Act: -0.1700
Data Index: 302305 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9314. Min Act: -0.1700
Data Index: 987714 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9399. Min Act: -0.1700
Data Index: 6373915 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9229. Min Act: -0.1700
Data Index: 8360683 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9229. Min Act: -0.1700
Data Index: 7852407 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9484. Min Act: -0.1699
Data Index: 8455701 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0582. Min Range: -2.0582
Max Act: 1.9399. Min Act: -0.1700
Data Index: 2464180 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19