Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 632 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.3589. Min Act: -0.1700
Data Index: 5304099 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.3589. Min Act: -0.1700
Data Index: 648189 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.3277. Min Act: -0.1700
Data Index: 4230929 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.2339. Min Act: -0.1700
Data Index: 7874384 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.2339. Min Act: -0.1700
Data Index: 294320 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.2027. Min Act: -0.1700
Data Index: 4014478 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.2027. Min Act: -0.1700
Data Index: 2094208 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.1714. Min Act: -0.1700
Data Index: 437433 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.1714. Min Act: -0.1700
Data Index: 5525350 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.1402. Min Act: -0.1700
Data Index: 3349237 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.1402. Min Act: -0.1700
Data Index: 4313659 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.1402. Min Act: -0.1700
Data Index: 1071434 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.1089. Min Act: -0.1700
Data Index: 3175438 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.1402. Min Act: -0.1700
Data Index: 1612630 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.1089. Min Act: -0.1700
Data Index: 3552937 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.0777. Min Act: -0.1700
Data Index: 1112655 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.1089. Min Act: -0.1700
Data Index: 5906405 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.0777. Min Act: -0.1700
Data Index: 5381869 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.0777. Min Act: -0.1700
Data Index: 3046905 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3589. Min Range: -5.3589
Max Act: 5.0777. Min Act: -0.1700
Data Index: 5868133 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19