Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 512 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.2123. Min Act: -0.1700
Data Index: 498531 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.1811. Min Act: -0.1700
Data Index: 340148 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.1186. Min Act: -0.1700
Data Index: 551578 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.1498. Min Act: -0.1700
Data Index: 156250 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.1186. Min Act: -0.1700
Data Index: 384331 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.0561. Min Act: -0.1700
Data Index: 200586 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.0873. Min Act: -0.1700
Data Index: 548634 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.0561. Min Act: -0.1700
Data Index: 603003 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.0561. Min Act: -0.1700
Data Index: 17189 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.0561. Min Act: -0.1700
Data Index: 470223 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.0561. Min Act: -0.1700
Data Index: 21725 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.0873. Min Act: -0.1700
Data Index: 751241 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.0561. Min Act: -0.1700
Data Index: 411565 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2123. Min Range: -5.2123
Max Act: 4.9936. Min Act: -0.1700
Data Index: 1140742 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2123. Min Range: -5.2123
Max Act: 4.9936. Min Act: -0.1700
Data Index: 308090 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2123. Min Range: -5.2123
Max Act: 4.9936. Min Act: -0.1700
Data Index: 1142921 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2123. Min Range: -5.2123
Max Act: 4.9936. Min Act: -0.1700
Data Index: 249437 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2123. Min Range: -5.2123
Max Act: 4.9936. Min Act: -0.1700
Data Index: 1182640 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2123. Min Range: -5.2123
Max Act: 4.9936. Min Act: -0.1700
Data Index: 1270343 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2123. Min Range: -5.2123
Max Act: 5.0248. Min Act: -0.1700
Data Index: 1090096 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19