Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1820 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.9947. Min Act: -0.1700
Data Index: 66517 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.6822. Min Act: -0.1700
Data Index: 1219819 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.6509. Min Act: -0.1700
Data Index: 868624 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.6197. Min Act: -0.1700
Data Index: 908625 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.5884. Min Act: -0.1700
Data Index: 708862 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.5572. Min Act: -0.1700
Data Index: 1298782 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.5259. Min Act: -0.1700
Data Index: 642963 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.4634. Min Act: -0.1698
Data Index: 550745 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.5259. Min Act: -0.1700
Data Index: 1100865 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.4634. Min Act: -0.1699
Data Index: 860574 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.4634. Min Act: -0.1690
Data Index: 1335449 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.4321. Min Act: -0.1700
Data Index: 566740 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.4009. Min Act: -0.1700
Data Index: 77843 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.4321. Min Act: -0.1700
Data Index: 1144935 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.4321. Min Act: -0.1698
Data Index: 190431 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.4009. Min Act: -0.1700
Data Index: 79478 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.4009. Min Act: -0.1698
Data Index: 305360 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.4009. Min Act: -0.1700
Data Index: 540180 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.4321. Min Act: -0.1699
Data Index: 1069132 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9947. Min Range: -4.9947
Max Act: 4.4009. Min Act: -0.1700
Data Index: 264739 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19