Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 321 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.4672. Min Act: -0.1700
Data Index: 893833 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.3735. Min Act: -0.1700
Data Index: 462164 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.4047. Min Act: -0.1700
Data Index: 893545 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.3110. Min Act: -0.1700
Data Index: 994979 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.2797. Min Act: -0.1700
Data Index: 100498 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.3110. Min Act: -0.1700
Data Index: 81125 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.2485. Min Act: -0.1700
Data Index: 994606 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.2485. Min Act: -0.1700
Data Index: 556829 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.2797. Min Act: -0.1700
Data Index: 180855 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.2172. Min Act: -0.1700
Data Index: 139559 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.2485. Min Act: -0.1700
Data Index: 148887 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.2485. Min Act: -0.1700
Data Index: 645943 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.2485. Min Act: -0.1700
Data Index: 1147459 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.2485. Min Act: -0.1700
Data Index: 600386 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.2485. Min Act: -0.1700
Data Index: 910841 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.2172. Min Act: -0.1700
Data Index: 359732 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.2172. Min Act: -0.1700
Data Index: 645527 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.1547. Min Act: -0.1700
Data Index: 768550 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.1860. Min Act: -0.1700
Data Index: 76525 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4672. Min Range: -4.4672
Max Act: 4.1860. Min Act: -0.1700
Data Index: 691836 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19