Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.4768. Min Act: -0.1700
Data Index: 475528 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.3830. Min Act: -0.1700
Data Index: 1263893 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.3830. Min Act: -0.1700
Data Index: 149158 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.4143. Min Act: -0.1700
Data Index: 452017 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.3518. Min Act: -0.1700
Data Index: 41759 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.3205. Min Act: -0.1700
Data Index: 453391 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.3205. Min Act: -0.1700
Data Index: 579127 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.2580. Min Act: -0.1697
Data Index: 676518 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.2736. Min Act: -0.1700
Data Index: 534497 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.2893. Min Act: -0.1700
Data Index: 796643 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.2580. Min Act: -0.1700
Data Index: 674988 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.2267. Min Act: -0.1700
Data Index: 1225943 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.2424. Min Act: -0.1700
Data Index: 717286 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.1173. Min Act: -0.1700
Data Index: 361150 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.2267. Min Act: -0.1700
Data Index: 1111772 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.1955. Min Act: -0.1700
Data Index: 948370 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.1799. Min Act: -0.1700
Data Index: 72054 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.1486. Min Act: -0.1700
Data Index: 549029 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.1799. Min Act: -0.1700
Data Index: 762196 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4768. Min Range: -4.4768
Max Act: 4.1330. Min Act: -0.1700
Data Index: 1057679 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19