Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1814 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.8592. Min Act: -0.1700
Data Index: 1975031 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.7654. Min Act: -0.1700
Data Index: 7444900 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.7029. Min Act: -0.1700
Data Index: 3437469 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.6092. Min Act: -0.1700
Data Index: 4362571 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.6092. Min Act: -0.1700
Data Index: 1583479 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.6092. Min Act: -0.1700
Data Index: 3139342 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.5779. Min Act: -0.1700
Data Index: 8097591 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.5779. Min Act: -0.1700
Data Index: 541490 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.5779. Min Act: -0.1700
Data Index: 7840842 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.5467. Min Act: -0.1700
Data Index: 5828270 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.5779. Min Act: -0.1700
Data Index: 2232153 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.5467. Min Act: -0.1700
Data Index: 3953997 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.5467. Min Act: -0.1700
Data Index: 1213344 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.5467. Min Act: -0.1700
Data Index: 2884974 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.5467. Min Act: -0.1700
Data Index: 2492189 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.5779. Min Act: -0.1700
Data Index: 6262470 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.5467. Min Act: -0.1700
Data Index: 1633629 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.5467. Min Act: -0.1700
Data Index: 569003 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.4842. Min Act: -0.1700
Data Index: 2230395 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8592. Min Range: -4.8592
Max Act: 4.4842. Min Act: -0.1700
Data Index: 543112 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19