Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 23 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.8949. Min Act: -0.1700
Data Index: 333193 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.7387. Min Act: -0.1700
Data Index: 216701 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.7074. Min Act: -0.1700
Data Index: 1054898 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.6449. Min Act: -0.1700
Data Index: 92496 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.6137. Min Act: -0.1700
Data Index: 1006102 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.5199. Min Act: -0.1700
Data Index: 378588 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.5512. Min Act: -0.1700
Data Index: 1061077 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.4262. Min Act: -0.1700
Data Index: 79337 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.4574. Min Act: -0.1700
Data Index: 601027 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.4262. Min Act: -0.1700
Data Index: 126277 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.4574. Min Act: -0.1700
Data Index: 1201320 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.4574. Min Act: -0.1700
Data Index: 1004004 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.3949. Min Act: -0.1700
Data Index: 337401 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.4262. Min Act: -0.1700
Data Index: 766870 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.3637. Min Act: -0.1700
Data Index: 61988 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.4262. Min Act: -0.1700
Data Index: 1089282 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.3637. Min Act: -0.1700
Data Index: 473281 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.3949. Min Act: -0.1700
Data Index: 640396 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.3949. Min Act: -0.1700
Data Index: 132163 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8949. Min Range: -4.8949
Max Act: 4.3324. Min Act: -0.1700
Data Index: 1194793 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19