Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2090 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.7124. Min Act: -0.1700
Data Index: 5725829 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.5874. Min Act: -0.1700
Data Index: 4151444 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.5874. Min Act: -0.1700
Data Index: 4256814 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.5249. Min Act: -0.1700
Data Index: 73526 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.5249. Min Act: -0.1700
Data Index: 3574464 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.4937. Min Act: -0.1700
Data Index: 1942712 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.4312. Min Act: -0.1700
Data Index: 8954 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.3687. Min Act: -0.1700
Data Index: 8470426 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.3374. Min Act: -0.1700
Data Index: 7079687 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.3374. Min Act: -0.1700
Data Index: 2856369 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.3687. Min Act: -0.1700
Data Index: 7946515 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.3062. Min Act: -0.1700
Data Index: 5505250 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.2749. Min Act: -0.1700
Data Index: 2169255 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.3062. Min Act: -0.1700
Data Index: 4765690 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.3062. Min Act: -0.1700
Data Index: 4067965 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.3062. Min Act: -0.1700
Data Index: 6302164 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.3062. Min Act: -0.1700
Data Index: 8756412 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.2437. Min Act: -0.1700
Data Index: 4754017 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.2749. Min Act: -0.1700
Data Index: 6355874 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7124. Min Range: -6.7124
Max Act: 6.2437. Min Act: -0.1700
Data Index: 1677718 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19