Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1142 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.7518. Min Act: -0.1700
Data Index: 574458 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.6268. Min Act: -0.1700
Data Index: 673937 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.5955. Min Act: -0.1700
Data Index: 243677 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.5643. Min Act: -0.1700
Data Index: 234111 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.5330. Min Act: -0.1700
Data Index: 1623391 (Python Code)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.5643. Min Act: -0.1700
Data Index: 1418055 (Python Code)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.4705. Min Act: -0.1700
Data Index: 174575 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.5018. Min Act: -0.1700
Data Index: 1541516 (Python Code)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.5018. Min Act: -0.1700
Data Index: 1379162 (Python Code)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.5018. Min Act: -0.1700
Data Index: 353843 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.4393. Min Act: -0.1700
Data Index: 814884 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.4393. Min Act: -0.1700
Data Index: 1082399 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.5330. Min Act: -0.1700
Data Index: 1357751 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.4705. Min Act: -0.1700
Data Index: 855850 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.4080. Min Act: -0.1700
Data Index: 1299507 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.4393. Min Act: -0.1700
Data Index: 1461781 (Python Code)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.4393. Min Act: -0.1700
Data Index: 1441126 (Python Code)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.4705. Min Act: -0.1700
Data Index: 1386872 (Python Code)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.3768. Min Act: -0.1700
Data Index: 1632093 (Python Code)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7518. Min Range: -4.7518
Max Act: 4.4705. Min Act: -0.1700
Data Index: 303630 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19