Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1807 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0975. Min Range: -4.0975
Max Act: 4.0975. Min Act: -0.1700
Data Index: 8196809 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0975. Min Range: -4.0975
Max Act: 4.0662. Min Act: -0.1700
Data Index: 1850448 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0975. Min Range: -4.0975
Max Act: 4.0349. Min Act: -0.1700
Data Index: 3069521 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.7848. Min Act: -0.1700
Data Index: 860937 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.7379. Min Act: -0.1700
Data Index: 1790290 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.7379. Min Act: -0.1700
Data Index: 8468112 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.7535. Min Act: -0.1700
Data Index: 663324 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.7223. Min Act: -0.1700
Data Index: 3599519 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.6910. Min Act: -0.1700
Data Index: 333404 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.6910. Min Act: -0.1700
Data Index: 6044951 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.7066. Min Act: -0.1700
Data Index: 5367572 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.6910. Min Act: -0.1700
Data Index: 1283866 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.6127. Min Act: -0.1700
Data Index: 3080720 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.6440. Min Act: -0.1700
Data Index: 1247099 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.6440. Min Act: -0.1700
Data Index: 4946481 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.6440. Min Act: -0.1700
Data Index: 1323046 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.6127. Min Act: -0.1700
Data Index: 3997802 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.5971. Min Act: -0.1700
Data Index: 8260101 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.5501. Min Act: -0.1700
Data Index: 1073016 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0975. Min Range: -4.0975
Max Act: 3.5188. Min Act: -0.1700
Data Index: 5044067 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19