Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1886 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.6232. Min Act: -0.1700
Data Index: 1220629 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.6232. Min Act: -0.1700
Data Index: 3276408 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.6232. Min Act: -0.1700
Data Index: 5274908 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.6232. Min Act: -0.1700
Data Index: 7070385 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.5920. Min Act: -0.1700
Data Index: 3137588 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.5920. Min Act: -0.1700
Data Index: 7923487 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.5607. Min Act: -0.1700
Data Index: 6639399 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.5607. Min Act: -0.1700
Data Index: 2675769 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.5295. Min Act: -0.1700
Data Index: 3515160 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.5295. Min Act: -0.1700
Data Index: 5380068 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.5295. Min Act: -0.1700
Data Index: 7738093 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.4670. Min Act: -0.1700
Data Index: 403419 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.4357. Min Act: -0.1700
Data Index: 5228284 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.4670. Min Act: -0.1700
Data Index: 7250152 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.4670. Min Act: -0.1700
Data Index: 3200703 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.4357. Min Act: -0.1700
Data Index: 459012 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.4357. Min Act: -0.1700
Data Index: 464822 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.4045. Min Act: -0.1700
Data Index: 618594 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.4357. Min Act: -0.1700
Data Index: 5560965 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6232. Min Range: -4.6232
Max Act: 4.4045. Min Act: -0.1700
Data Index: 3814238 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19