Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1581 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.1430. Min Range: -3.1430
Max Act: 3.1430. Min Act: -0.1700
Data Index: 693877 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1430. Min Range: -3.1430
Max Act: 3.0642. Min Act: -0.1700
Data Index: 253271 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.9377. Min Act: -0.1700
Data Index: 754854 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.8902. Min Act: -0.1700
Data Index: 324440 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.8902. Min Act: -0.1700
Data Index: 727444 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.8743. Min Act: -0.1700
Data Index: 835913 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.8743. Min Act: -0.1700
Data Index: 1211550 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.8584. Min Act: -0.1700
Data Index: 1270438 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.8425. Min Act: -0.1700
Data Index: 119739 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.8425. Min Act: -0.1700
Data Index: 1158704 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.8425. Min Act: -0.1700
Data Index: 617633 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.8266. Min Act: -0.1700
Data Index: 1304408 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.8266. Min Act: -0.1700
Data Index: 254860 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.8107. Min Act: -0.1700
Data Index: 103395 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.7948. Min Act: -0.1700
Data Index: 523955 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.8107. Min Act: -0.1700
Data Index: 643587 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.7948. Min Act: -0.1700
Data Index: 1075885 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.7948. Min Act: -0.1700
Data Index: 1219500 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.7948. Min Act: -0.1700
Data Index: 532568 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1430. Min Range: -3.1430
Max Act: 2.8107. Min Act: -0.1700
Data Index: 270395 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19