Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2454 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1486. Min Range: -8.1486
Max Act: 8.1486. Min Act: -0.1700
Data Index: 4599883 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.9611. Min Act: -0.1700
Data Index: 5846579 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1486. Min Range: -8.1486
Max Act: 8.0236. Min Act: -0.1700
Data Index: 2934441 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.7111. Min Act: -0.1700
Data Index: 4073518 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.7111. Min Act: -0.1700
Data Index: 4264884 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.7111. Min Act: -0.1700
Data Index: 7850916 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.7111. Min Act: -0.1700
Data Index: 7422190 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.7111. Min Act: -0.1700
Data Index: 1440321 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.7111. Min Act: -0.1700
Data Index: 7878955 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.5861. Min Act: -0.1700
Data Index: 348386 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.6486. Min Act: -0.1700
Data Index: 2093606 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.7111. Min Act: -0.1700
Data Index: 8626408 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.7111. Min Act: -0.1700
Data Index: 6051384 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.7111. Min Act: -0.1700
Data Index: 4857753 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.6486. Min Act: -0.1700
Data Index: 147872 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.5861. Min Act: -0.1700
Data Index: 805313 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.5861. Min Act: -0.1700
Data Index: 530334 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.5861. Min Act: -0.1700
Data Index: 5136062 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.6486. Min Act: -0.1700
Data Index: 308212 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1486. Min Range: -8.1486
Max Act: 7.4611. Min Act: -0.1700
Data Index: 5427497 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19