Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 632 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.2441. Min Act: -0.1700
Data Index: 2504172 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.1191. Min Act: -0.1700
Data Index: 2504169 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.9628. Min Act: -0.1700
Data Index: 2504170 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.9628. Min Act: -0.1700
Data Index: 2504159 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.9315. Min Act: -0.1700
Data Index: 2504164 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.9628. Min Act: -0.1700
Data Index: 2504165 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.9315. Min Act: -0.1700
Data Index: 8279876 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.9002. Min Act: -0.1700
Data Index: 2504171 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.9002. Min Act: -0.1700
Data Index: 2504160 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.8064. Min Act: -0.1700
Data Index: 2236611 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.8064. Min Act: -0.1700
Data Index: 5180645 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.7752. Min Act: -0.1700
Data Index: 6817414 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.7752. Min Act: -0.1700
Data Index: 3065859 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.7439. Min Act: -0.1700
Data Index: 6034638 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.7439. Min Act: -0.1700
Data Index: 1419556 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.7439. Min Act: -0.1700
Data Index: 3301913 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.7439. Min Act: -0.1700
Data Index: 3301914 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.7439. Min Act: -0.1700
Data Index: 3065856 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.6813. Min Act: -0.1700
Data Index: 5507650 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2441. Min Range: -4.2441
Max Act: 3.6500. Min Act: -0.1700
Data Index: 2012266 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19