Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1574. Min Range: -5.1574
Max Act: 5.1574. Min Act: -0.1700
Data Index: 1030845 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1574. Min Range: -5.1574
Max Act: 5.1574. Min Act: -0.1700
Data Index: 3090297 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1574. Min Range: -5.1574
Max Act: 5.0949. Min Act: -0.1700
Data Index: 8236162 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1574. Min Range: -5.1574
Max Act: 5.0324. Min Act: -0.1700
Data Index: 707942 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1574. Min Range: -5.1574
Max Act: 5.0011. Min Act: -0.1700
Data Index: 7153262 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1574. Min Range: -5.1574
Max Act: 5.0011. Min Act: -0.1700
Data Index: 660661 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9386. Min Act: -0.1700
Data Index: 2491910 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9699. Min Act: -0.1700
Data Index: 5823867 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9386. Min Act: -0.1700
Data Index: 5712280 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9386. Min Act: -0.1700
Data Index: 2127510 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9386. Min Act: -0.1700
Data Index: 7464325 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9386. Min Act: -0.1700
Data Index: 1638633 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9386. Min Act: -0.1700
Data Index: 3126852 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9386. Min Act: -0.1700
Data Index: 7127737 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9386. Min Act: -0.1700
Data Index: 8050586 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9386. Min Act: -0.1700
Data Index: 5645297 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9386. Min Act: -0.1700
Data Index: 373690 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9386. Min Act: -0.1700
Data Index: 6953941 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9386. Min Act: -0.1700
Data Index: 4792339 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1574. Min Range: -5.1574
Max Act: 4.9386. Min Act: -0.1700
Data Index: 6037646 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19