Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2039 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.5559. Min Act: -0.1700
Data Index: 887300 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.4750. Min Act: -0.1700
Data Index: 366198 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.4588. Min Act: -0.1700
Data Index: 208666 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.4588. Min Act: -0.1700
Data Index: 1190753 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.4263. Min Act: -0.1700
Data Index: 1150571 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.4100. Min Act: -0.1700
Data Index: 218636 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.4263. Min Act: -0.1700
Data Index: 169610 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.4263. Min Act: -0.1700
Data Index: 1245310 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.4263. Min Act: -0.1700
Data Index: 385208 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.4100. Min Act: -0.1700
Data Index: 1211820 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.3937. Min Act: -0.1700
Data Index: 739697 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.3937. Min Act: -0.1700
Data Index: 794496 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.3773. Min Act: -0.1700
Data Index: 354630 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.3610. Min Act: -0.1700
Data Index: 608088 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.3773. Min Act: -0.1700
Data Index: 859874 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.3937. Min Act: -0.1700
Data Index: 549147 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.3937. Min Act: -0.1700
Data Index: 1125559 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.3610. Min Act: -0.1700
Data Index: 327753 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.3610. Min Act: -0.1700
Data Index: 55962 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5559. Min Range: -2.5559
Max Act: 2.3610. Min Act: -0.1700
Data Index: 367693 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19