Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 769 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0611. Min Range: -2.0611
Max Act: 2.0611. Min Act: -0.1700
Data Index: 6573612 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0611. Min Range: -2.0611
Max Act: 2.0611. Min Act: -0.1700
Data Index: 7843601 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0611. Min Range: -2.0611
Max Act: 2.0442. Min Act: -0.1700
Data Index: 4589609 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0611. Min Range: -2.0611
Max Act: 2.0274. Min Act: -0.1700
Data Index: 5122215 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0611. Min Range: -2.0611
Max Act: 2.0274. Min Act: -0.1700
Data Index: 5149234 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0611. Min Range: -2.0611
Max Act: 2.0105. Min Act: -0.1700
Data Index: 648810 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9936. Min Act: -0.1700
Data Index: 5722729 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9767. Min Act: -0.1700
Data Index: 7081890 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9767. Min Act: -0.1700
Data Index: 7572828 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9598. Min Act: -0.1700
Data Index: 5960516 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9598. Min Act: -0.1700
Data Index: 3170487 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9598. Min Act: -0.1700
Data Index: 6844374 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9598. Min Act: -0.1700
Data Index: 3168160 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9428. Min Act: -0.1700
Data Index: 3910113 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9428. Min Act: -0.1700
Data Index: 7538017 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9428. Min Act: -0.1700
Data Index: 3691843 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9428. Min Act: -0.1695
Data Index: 31428 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9428. Min Act: -0.1700
Data Index: 7601068 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9258. Min Act: -0.1700
Data Index: 7606954 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0611. Min Range: -2.0611
Max Act: 1.9428. Min Act: -0.1700
Data Index: 4290887 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19