Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 993 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1135. Min Range: -6.1135
Max Act: 6.0823. Min Act: -0.1700
Data Index: 5679206 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1135. Min Range: -6.1135
Max Act: 6.1135. Min Act: -0.1700
Data Index: 3150667 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1135. Min Range: -6.1135
Max Act: 6.0198. Min Act: -0.1700
Data Index: 4570857 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.9885. Min Act: -0.1700
Data Index: 8562550 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1135. Min Range: -6.1135
Max Act: 6.0510. Min Act: -0.1700
Data Index: 504691 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1135. Min Range: -6.1135
Max Act: 6.0198. Min Act: -0.1700
Data Index: 899968 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1135. Min Range: -6.1135
Max Act: 6.0510. Min Act: -0.1700
Data Index: 5679210 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.9885. Min Act: -0.1700
Data Index: 1121542 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.9573. Min Act: -0.1700
Data Index: 7315459 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.9573. Min Act: -0.1700
Data Index: 524566 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.9573. Min Act: -0.1700
Data Index: 2857646 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.9573. Min Act: -0.1700
Data Index: 1805118 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.9260. Min Act: -0.1700
Data Index: 5679215 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.9573. Min Act: -0.1700
Data Index: 6954781 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.8948. Min Act: -0.1700
Data Index: 4693923 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.8635. Min Act: -0.1700
Data Index: 5679208 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.9260. Min Act: -0.1700
Data Index: 384981 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.8948. Min Act: -0.1700
Data Index: 6650212 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.8948. Min Act: -0.1700
Data Index: 7546223 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.8948. Min Act: -0.1700
Data Index: 1394350 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19