Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2903 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.9170. Min Act: -0.1700
Data Index: 6132525 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.9011. Min Act: -0.1700
Data Index: 1955166 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8694. Min Act: -0.1700
Data Index: 4898506 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.9011. Min Act: -0.1700
Data Index: 3396649 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8853. Min Act: -0.1700
Data Index: 8199015 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8535. Min Act: -0.1700
Data Index: 4015348 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8694. Min Act: -0.1700
Data Index: 8253212 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8535. Min Act: -0.1700
Data Index: 2940358 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8535. Min Act: -0.1700
Data Index: 4466523 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8694. Min Act: -0.1700
Data Index: 2848036 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8535. Min Act: -0.1700
Data Index: 3592768 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8376. Min Act: -0.1700
Data Index: 8238603 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8376. Min Act: -0.1700
Data Index: 5213617 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8535. Min Act: -0.1700
Data Index: 1166742 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8217. Min Act: -0.1700
Data Index: 2785379 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8058. Min Act: -0.1700
Data Index: 2719897 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8217. Min Act: -0.1700
Data Index: 7948664 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8535. Min Act: -0.1700
Data Index: 3087825 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8535. Min Act: -0.1700
Data Index: 4904915 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9170. Min Range: -2.9170
Max Act: 2.8217. Min Act: -0.1700
Data Index: 726359 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19