Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1907 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.7162. Min Act: -0.1700
Data Index: 436371 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.7162. Min Act: -0.1700
Data Index: 75807 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6842. Min Act: -0.1700
Data Index: 782991 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6521. Min Act: -0.1700
Data Index: 826038 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6360. Min Act: -0.1700
Data Index: 397973 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6521. Min Act: -0.1700
Data Index: 312313 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6521. Min Act: -0.1700
Data Index: 1207435 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6681. Min Act: -0.1700
Data Index: 629067 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6360. Min Act: -0.1700
Data Index: 79074 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6360. Min Act: -0.1700
Data Index: 645076 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6360. Min Act: -0.1700
Data Index: 104110 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6200. Min Act: -0.1700
Data Index: 1216703 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6360. Min Act: -0.1700
Data Index: 938824 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6360. Min Act: -0.1700
Data Index: 229566 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6200. Min Act: -0.1700
Data Index: 1535458 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6200. Min Act: -0.1700
Data Index: 489362 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6200. Min Act: -0.1700
Data Index: 675146 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6039. Min Act: -0.1700
Data Index: 515464 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6039. Min Act: -0.1700
Data Index: 1048526 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7162. Min Range: -2.7162
Max Act: 2.6200. Min Act: -0.1700
Data Index: 527875 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19