Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8042. Min Range: -5.8042
Max Act: 5.8042. Min Act: -0.1700
Data Index: 4534136 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8042. Min Range: -5.8042
Max Act: 5.7730. Min Act: -0.1700
Data Index: 6849593 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8042. Min Range: -5.8042
Max Act: 5.3667. Min Act: -0.1700
Data Index: 482411 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8042. Min Range: -5.8042
Max Act: 5.0855. Min Act: -0.1700
Data Index: 2963094 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8042. Min Range: -5.8042
Max Act: 5.0230. Min Act: -0.1700
Data Index: 6756702 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8042. Min Range: -5.8042
Max Act: 5.0230. Min Act: -0.1700
Data Index: 2330368 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.9917. Min Act: -0.1700
Data Index: 4570799 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.9917. Min Act: -0.1700
Data Index: 7136714 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.9917. Min Act: -0.1700
Data Index: 7577105 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.9917. Min Act: -0.1700
Data Index: 1110799 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.9917. Min Act: -0.1700
Data Index: 5170235 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.9605. Min Act: -0.1700
Data Index: 1190512 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.9292. Min Act: -0.1700
Data Index: 7647242 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.9917. Min Act: -0.1700
Data Index: 2329170 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.9917. Min Act: -0.1700
Data Index: 1034852 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.8980. Min Act: -0.1700
Data Index: 2549681 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.9292. Min Act: -0.1700
Data Index: 3420456 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.9292. Min Act: -0.1700
Data Index: 3425426 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.9292. Min Act: -0.1700
Data Index: 3664716 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8042. Min Range: -5.8042
Max Act: 4.9292. Min Act: -0.1700
Data Index: 3707440 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19