Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 901 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3164. Min Range: -6.3164
Max Act: 6.3164. Min Act: -0.1700
Data Index: 3793829 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3164. Min Range: -6.3164
Max Act: 6.1289. Min Act: -0.1700
Data Index: 1667008 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3164. Min Range: -6.3164
Max Act: 6.0352. Min Act: -0.1700
Data Index: 7987642 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3164. Min Range: -6.3164
Max Act: 6.0352. Min Act: -0.1700
Data Index: 4483489 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.9727. Min Act: -0.1700
Data Index: 7672534 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.9102. Min Act: -0.1700
Data Index: 6791155 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.8789. Min Act: -0.1700
Data Index: 3486928 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.7539. Min Act: -0.1700
Data Index: 4729548 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.7852. Min Act: -0.1700
Data Index: 3498545 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.7852. Min Act: -0.1700
Data Index: 4475096 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.7227. Min Act: -0.1700
Data Index: 6176628 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.7539. Min Act: -0.1700
Data Index: 6850356 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.7227. Min Act: -0.1700
Data Index: 3225289 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.7227. Min Act: -0.1700
Data Index: 712763 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.7227. Min Act: -0.1700
Data Index: 6968031 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.6914. Min Act: -0.1700
Data Index: 5015292 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.7227. Min Act: -0.1700
Data Index: 6657681 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.6914. Min Act: -0.1700
Data Index: 7077172 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.6914. Min Act: -0.1700
Data Index: 5157473 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3164. Min Range: -6.3164
Max Act: 5.6602. Min Act: -0.1700
Data Index: 1078333 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19