Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 143 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7589. Min Act: -0.1700
Data Index: 660056 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7503. Min Act: -0.1699
Data Index: 7479661 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7416. Min Act: -0.1700
Data Index: 2156541 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7330. Min Act: -0.1700
Data Index: 546377 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7330. Min Act: -0.1700
Data Index: 389288 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7330. Min Act: -0.1700
Data Index: 6465691 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7330. Min Act: -0.1700
Data Index: 2640338 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7243. Min Act: -0.1700
Data Index: 512644 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7157. Min Act: -0.1700
Data Index: 3871855 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7157. Min Act: -0.1700
Data Index: 4749867 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7243. Min Act: -0.1700
Data Index: 5615101 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7243. Min Act: -0.1699
Data Index: 373061 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7157. Min Act: -0.1700
Data Index: 4189139 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7157. Min Act: -0.1700
Data Index: 116011 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7243. Min Act: -0.1700
Data Index: 3426143 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.6983. Min Act: -0.1700
Data Index: 291779 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.7157. Min Act: -0.1700
Data Index: 2643963 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.6897. Min Act: -0.1700
Data Index: 645379 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.6897. Min Act: -0.1700
Data Index: 3594203 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7589. Min Range: -1.7589
Max Act: 1.6983. Min Act: -0.1700
Data Index: 3290259 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19