Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2017 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.3576. Min Act: -0.1700
Data Index: 678779 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.3249. Min Act: -0.1700
Data Index: 176561 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.3249. Min Act: -0.1700
Data Index: 530760 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.3249. Min Act: -0.1700
Data Index: 1289432 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.3084. Min Act: -0.1700
Data Index: 863526 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.3084. Min Act: -0.1700
Data Index: 893071 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2755. Min Act: -0.1700
Data Index: 1132958 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2591. Min Act: -0.1700
Data Index: 1260405 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2425. Min Act: -0.1700
Data Index: 327898 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2425. Min Act: -0.1700
Data Index: 133960 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2425. Min Act: -0.1700
Data Index: 367597 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2425. Min Act: -0.1700
Data Index: 272240 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2591. Min Act: -0.1700
Data Index: 887673 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2591. Min Act: -0.1700
Data Index: 365784 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2591. Min Act: -0.1700
Data Index: 1148218 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2591. Min Act: -0.1700
Data Index: 83370 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2755. Min Act: -0.1700
Data Index: 327312 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2591. Min Act: -0.1700
Data Index: 937347 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2425. Min Act: -0.1700
Data Index: 245671 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3576. Min Range: -2.3576
Max Act: 2.2425. Min Act: -0.1700
Data Index: 857717 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19