Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1780 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.4560. Min Act: -0.1700
Data Index: 196535 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.4560. Min Act: -0.1700
Data Index: 1096642 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.4248. Min Act: -0.1700
Data Index: 45355 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.3935. Min Act: -0.1700
Data Index: 7441 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.3935. Min Act: -0.1700
Data Index: 842253 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.3623. Min Act: -0.1700
Data Index: 813275 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.3623. Min Act: -0.1700
Data Index: 805902 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.3935. Min Act: -0.1700
Data Index: 1352891 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.3310. Min Act: -0.1700
Data Index: 963501 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.2998. Min Act: -0.1700
Data Index: 1388028 (Python Code)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.2998. Min Act: -0.1700
Data Index: 1138227 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.3310. Min Act: -0.1700
Data Index: 938990 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.3310. Min Act: -0.1700
Data Index: 847548 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.2685. Min Act: -0.1700
Data Index: 434164 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.2998. Min Act: -0.1700
Data Index: 564033 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.2998. Min Act: -0.1700
Data Index: 875474 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.2998. Min Act: -0.1700
Data Index: 675142 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.2998. Min Act: -0.1700
Data Index: 19724 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.2998. Min Act: -0.1700
Data Index: 1341959 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4560. Min Range: -4.4560
Max Act: 4.2372. Min Act: -0.1700
Data Index: 589279 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19