Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1461 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.7578. Min Act: -0.1700
Data Index: 303540 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.7419. Min Act: -0.1700
Data Index: 548865 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.7259. Min Act: -0.1700
Data Index: 1628742 (Python Code)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.7099. Min Act: -0.1700
Data Index: 1505081 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.7099. Min Act: -0.1700
Data Index: 1561882 (Python Code)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6939. Min Act: -0.1700
Data Index: 1511118 (Python Code)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.7099. Min Act: -0.1700
Data Index: 250546 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6939. Min Act: -0.1700
Data Index: 147519 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6939. Min Act: -0.1700
Data Index: 1515570 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.7099. Min Act: -0.1700
Data Index: 1490410 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6619. Min Act: -0.1700
Data Index: 510948 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6779. Min Act: -0.1700
Data Index: 1399533 (Python Code)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6779. Min Act: -0.1700
Data Index: 1551897 (Python Code)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6779. Min Act: -0.1700
Data Index: 1376953 (Python Code)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6619. Min Act: -0.1700
Data Index: 1411305 (Python Code)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6619. Min Act: -0.1700
Data Index: 801005 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6779. Min Act: -0.1700
Data Index: 516808 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6779. Min Act: -0.1700
Data Index: 792510 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6619. Min Act: -0.1700
Data Index: 37681 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6619. Min Act: -0.1700
Data Index: 419863 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19