Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 31 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.8951. Min Act: -0.1700
Data Index: 3868780 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.8794. Min Act: -0.1700
Data Index: 3868747 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.8482. Min Act: -0.1700
Data Index: 8137255 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.8482. Min Act: -0.1700
Data Index: 7669647 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.7856. Min Act: -0.1700
Data Index: 5665227 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.7856. Min Act: -0.1700
Data Index: 4290429 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.7856. Min Act: -0.1700
Data Index: 3586919 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.7231. Min Act: -0.1700
Data Index: 770464 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.7387. Min Act: -0.1700
Data Index: 3306906 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.7387. Min Act: -0.1700
Data Index: 6025603 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.7387. Min Act: -0.1700
Data Index: 1173683 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.7074. Min Act: -0.1700
Data Index: 5305992 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.6918. Min Act: -0.1700
Data Index: 938874 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.6918. Min Act: -0.1700
Data Index: 5753417 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.7074. Min Act: -0.1700
Data Index: 6094133 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.6761. Min Act: -0.1700
Data Index: 8419927 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.6761. Min Act: -0.1700
Data Index: 3631703 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.6605. Min Act: -0.1700
Data Index: 2009404 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.6761. Min Act: -0.1700
Data Index: 5538807 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8951. Min Range: -3.8951
Max Act: 3.6605. Min Act: -0.1700
Data Index: 2497034 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19