Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1073 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.6731. Min Act: -0.1700
Data Index: 5446320 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.6731. Min Act: -0.1700
Data Index: 2095404 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.6106. Min Act: -0.1700
Data Index: 4789163 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.4231. Min Act: -0.1700
Data Index: 588613 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.4231. Min Act: -0.1700
Data Index: 4189301 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.3606. Min Act: -0.1700
Data Index: 6392979 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.3606. Min Act: -0.1700
Data Index: 3577383 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.2981. Min Act: -0.1700
Data Index: 900087 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.2356. Min Act: -0.1700
Data Index: 1629245 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.2356. Min Act: -0.1700
Data Index: 5048292 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.1731. Min Act: -0.1700
Data Index: 384856 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.2356. Min Act: -0.1700
Data Index: 4767072 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.2356. Min Act: -0.1700
Data Index: 603473 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.2356. Min Act: -0.1700
Data Index: 5918993 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.2356. Min Act: -0.1700
Data Index: 7445671 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.1731. Min Act: -0.1700
Data Index: 992149 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.1731. Min Act: -0.1700
Data Index: 514677 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.1106. Min Act: -0.1700
Data Index: 6147439 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.1106. Min Act: -0.1700
Data Index: 1809516 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6731. Min Range: -8.6731
Max Act: 8.2356. Min Act: -0.1700
Data Index: 7275808 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19