Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 102 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.4262. Min Act: -0.1700
Data Index: 976259 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.4262. Min Act: -0.1700
Data Index: 325557 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3936. Min Act: -0.1700
Data Index: 934294 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3772. Min Act: -0.1700
Data Index: 734510 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3772. Min Act: -0.1700
Data Index: 1126640 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3772. Min Act: -0.1700
Data Index: 391578 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3609. Min Act: -0.1700
Data Index: 447240 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3609. Min Act: -0.1700
Data Index: 917259 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3609. Min Act: -0.1700
Data Index: 394339 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3609. Min Act: -0.1700
Data Index: 783816 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3445. Min Act: -0.1700
Data Index: 781525 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3445. Min Act: -0.1700
Data Index: 1358945 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3281. Min Act: -0.1700
Data Index: 1327645 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3281. Min Act: -0.1700
Data Index: 1348075 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3281. Min Act: -0.1700
Data Index: 290424 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3117. Min Act: -0.1700
Data Index: 276667 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3281. Min Act: -0.1700
Data Index: 480987 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3445. Min Act: -0.1700
Data Index: 346391 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3117. Min Act: -0.1700
Data Index: 1521022 (Python Code)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4262. Min Range: -2.4262
Max Act: 2.3281. Min Act: -0.1700
Data Index: 155611 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19