Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 214 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.7611. Min Act: -0.1700
Data Index: 596213 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.7771. Min Act: -0.1700
Data Index: 1000889 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.7132. Min Act: -0.1700
Data Index: 1090738 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.6652. Min Act: -0.1700
Data Index: 490931 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.6491. Min Act: -0.1700
Data Index: 1336929 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.6491. Min Act: -0.1700
Data Index: 1316551 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.6331. Min Act: -0.1700
Data Index: 345394 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.6491. Min Act: -0.1700
Data Index: 593416 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.6170. Min Act: -0.1700
Data Index: 689677 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.5848. Min Act: -0.1700
Data Index: 279771 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.5687. Min Act: -0.1700
Data Index: 139610 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.5687. Min Act: -0.1700
Data Index: 891353 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.5848. Min Act: -0.1700
Data Index: 626780 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.5848. Min Act: -0.1700
Data Index: 810491 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.5848. Min Act: -0.1700
Data Index: 540344 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.5687. Min Act: -0.1700
Data Index: 161837 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.5526. Min Act: -0.1700
Data Index: 424167 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.5687. Min Act: -0.1700
Data Index: 306543 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.5526. Min Act: -0.1700
Data Index: 496127 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7771. Min Range: -2.7771
Max Act: 2.5364. Min Act: -0.1700
Data Index: 151177 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19