Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 727 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.3176. Min Range: -5.3176
Max Act: 5.3176. Min Act: -0.1700
Data Index: 585925 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3176. Min Range: -5.3176
Max Act: 5.2238. Min Act: -0.1700
Data Index: 349398 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3176. Min Range: -5.3176
Max Act: 5.0676. Min Act: -0.1700
Data Index: 934786 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3176. Min Range: -5.3176
Max Act: 5.0051. Min Act: -0.1700
Data Index: 1193345 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3176. Min Range: -5.3176
Max Act: 5.0363. Min Act: -0.1700
Data Index: 410678 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.9738. Min Act: -0.1700
Data Index: 736548 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.9738. Min Act: -0.1700
Data Index: 698769 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.9738. Min Act: -0.1700
Data Index: 661386 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.8801. Min Act: -0.1700
Data Index: 618166 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.9426. Min Act: -0.1700
Data Index: 369902 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.8801. Min Act: -0.1700
Data Index: 1240644 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.9426. Min Act: -0.1700
Data Index: 91233 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.8801. Min Act: -0.1700
Data Index: 315569 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.8176. Min Act: -0.1700
Data Index: 91442 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.8801. Min Act: -0.1700
Data Index: 506353 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.8488. Min Act: -0.1700
Data Index: 1330840 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.8176. Min Act: -0.1700
Data Index: 717821 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.8176. Min Act: -0.1700
Data Index: 177628 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.7863. Min Act: -0.1700
Data Index: 563647 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3176. Min Range: -5.3176
Max Act: 4.7863. Min Act: -0.1700
Data Index: 744987 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19