Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1287 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.9350. Min Act: -0.1700
Data Index: 449908 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.9032. Min Act: -0.1700
Data Index: 1218216 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.7760. Min Act: -0.1700
Data Index: 106303 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.7282. Min Act: -0.1700
Data Index: 362298 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.7282. Min Act: -0.1700
Data Index: 64135 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.6962. Min Act: -0.1700
Data Index: 1289255 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.6641. Min Act: -0.1700
Data Index: 117219 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.6641. Min Act: -0.1700
Data Index: 1200176 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.6481. Min Act: -0.1700
Data Index: 23112 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.5999. Min Act: -0.1700
Data Index: 298287 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.5999. Min Act: -0.1700
Data Index: 339965 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.5677. Min Act: -0.1700
Data Index: 688857 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.5838. Min Act: -0.1700
Data Index: 545249 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.5677. Min Act: -0.1700
Data Index: 202744 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.5677. Min Act: -0.1700
Data Index: 867643 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.5515. Min Act: -0.1700
Data Index: 406179 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.5354. Min Act: -0.1700
Data Index: 659368 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.5515. Min Act: -0.1700
Data Index: 1123205 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.5515. Min Act: -0.1700
Data Index: 1126412 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9350. Min Range: -2.9350
Max Act: 2.5515. Min Act: -0.1700
Data Index: 572469 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19