Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0589. Min Range: -5.0589
Max Act: 5.0589. Min Act: -0.1700
Data Index: 3104689 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0589. Min Range: -5.0589
Max Act: 5.0589. Min Act: -0.1700
Data Index: 1600103 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.9964. Min Act: -0.1700
Data Index: 1377310 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.9964. Min Act: -0.1700
Data Index: 8193222 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.9964. Min Act: -0.1700
Data Index: 3827249 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.9652. Min Act: -0.1700
Data Index: 8639225 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.9339. Min Act: -0.1700
Data Index: 617036 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.9027. Min Act: -0.1700
Data Index: 1966536 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.8714. Min Act: -0.1700
Data Index: 7619293 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.8402. Min Act: -0.1700
Data Index: 41208 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.8714. Min Act: -0.1688
Data Index: 6931197 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.8714. Min Act: -0.1700
Data Index: 3974505 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.8402. Min Act: -0.1700
Data Index: 2091038 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.8089. Min Act: -0.1700
Data Index: 3590780 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.8089. Min Act: -0.1700
Data Index: 1420992 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.8089. Min Act: -0.1700
Data Index: 2053120 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.8089. Min Act: -0.1700
Data Index: 2466559 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.8089. Min Act: -0.1700
Data Index: 4009754 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.8089. Min Act: -0.1700
Data Index: 1381484 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0589. Min Range: -5.0589
Max Act: 4.8089. Min Act: -0.1700
Data Index: 3275388 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19