Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1852 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.3961. Min Act: -0.1700
Data Index: 892862 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.3961. Min Act: -0.1700
Data Index: 4253191 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.3336. Min Act: -0.1700
Data Index: 393155 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.3336. Min Act: -0.1700
Data Index: 8366503 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.2711. Min Act: -0.1700
Data Index: 3428068 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.3024. Min Act: -0.1700
Data Index: 965126 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.2711. Min Act: -0.1700
Data Index: 8456613 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.2711. Min Act: -0.1700
Data Index: 3856081 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.2711. Min Act: -0.1700
Data Index: 781247 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.2711. Min Act: -0.1700
Data Index: 4698978 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.2711. Min Act: -0.1700
Data Index: 781248 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.2399. Min Act: -0.1700
Data Index: 8456612 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.1773. Min Act: -0.1700
Data Index: 965128 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.1773. Min Act: -0.1700
Data Index: 3428070 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.1773. Min Act: -0.1700
Data Index: 5519711 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.1773. Min Act: -0.1700
Data Index: 6687486 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.1461. Min Act: -0.1700
Data Index: 5158887 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.1461. Min Act: -0.1700
Data Index: 6132354 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.1461. Min Act: -0.1700
Data Index: 4318973 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3961. Min Range: -4.3961
Max Act: 4.1461. Min Act: -0.1700
Data Index: 7903761 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19