Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1948 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.4773. Min Act: -0.1700
Data Index: 333628 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.4773. Min Act: -0.1700
Data Index: 1312902 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.4448. Min Act: -0.1700
Data Index: 543381 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.4448. Min Act: -0.1700
Data Index: 51672 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.4448. Min Act: -0.1700
Data Index: 847164 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.4448. Min Act: -0.1700
Data Index: 241705 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.4286. Min Act: -0.1700
Data Index: 585603 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.4123. Min Act: -0.1700
Data Index: 604671 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.4123. Min Act: -0.1700
Data Index: 105565 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.4123. Min Act: -0.1700
Data Index: 942900 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.4123. Min Act: -0.1700
Data Index: 376088 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.4123. Min Act: -0.1700
Data Index: 1095241 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.4123. Min Act: -0.1700
Data Index: 817089 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.3960. Min Act: -0.1700
Data Index: 1354554 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.3960. Min Act: -0.1700
Data Index: 167315 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.3960. Min Act: -0.1700
Data Index: 686587 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.3960. Min Act: -0.1700
Data Index: 34807 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.3796. Min Act: -0.1700
Data Index: 817745 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.3960. Min Act: -0.1700
Data Index: 1247486 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4773. Min Range: -2.4773
Max Act: 2.3960. Min Act: -0.1699
Data Index: 796693 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19