Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1865 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.4146. Min Range: -3.4146
Max Act: 3.4146. Min Act: -0.1700
Data Index: 784054 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4146. Min Range: -3.4146
Max Act: 3.2576. Min Act: -0.1700
Data Index: 169061 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4146. Min Range: -3.4146
Max Act: 3.2105. Min Act: -0.1700
Data Index: 1442105 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4146. Min Range: -3.4146
Max Act: 3.1318. Min Act: -0.1700
Data Index: 157187 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4146. Min Range: -3.4146
Max Act: 3.1318. Min Act: -0.1700
Data Index: 710261 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4146. Min Range: -3.4146
Max Act: 3.0687. Min Act: -0.1700
Data Index: 1200066 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4146. Min Range: -3.4146
Max Act: 3.0529. Min Act: -0.1700
Data Index: 286202 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4146. Min Range: -3.4146
Max Act: 3.0055. Min Act: -0.1700
Data Index: 814896 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4146. Min Range: -3.4146
Max Act: 2.9897. Min Act: -0.1700
Data Index: 466059 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4146. Min Range: -3.4146
Max Act: 2.9739. Min Act: -0.1700
Data Index: 479645 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4146. Min Range: -3.4146
Max Act: 2.9581. Min Act: -0.1700
Data Index: 1518496 (Python Code)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4146. Min Range: -3.4146
Max Act: 2.9581. Min Act: -0.1700
Data Index: 90532 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4146. Min Range: -3.4146
Max Act: 2.9422. Min Act: -0.1700
Data Index: 1209085 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4146. Min Range: -3.4146
Max Act: 2.9422. Min Act: -0.1700
Data Index: 441486 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4146. Min Range: -3.4146
Max Act: 2.9264. Min Act: -0.1700
Data Index: 1329944 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4146. Min Range: -3.4146
Max Act: 2.9264. Min Act: -0.1700
Data Index: 801739 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4146. Min Range: -3.4146
Max Act: 2.9264. Min Act: -0.1700
Data Index: 699645 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4146. Min Range: -3.4146
Max Act: 2.9105. Min Act: -0.1700
Data Index: 786616 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4146. Min Range: -3.4146
Max Act: 2.8947. Min Act: -0.1700
Data Index: 355445 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4146. Min Range: -3.4146
Max Act: 2.8947. Min Act: -0.1700
Data Index: 641009 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19