Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1978 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1413. Min Range: -4.1413
Max Act: 4.1413. Min Act: -0.1700
Data Index: 525377 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1413. Min Range: -4.1413
Max Act: 4.0788. Min Act: -0.1700
Data Index: 1109574 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1413. Min Range: -4.1413
Max Act: 4.0788. Min Act: -0.1700
Data Index: 134281 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1413. Min Range: -4.1413
Max Act: 4.0476. Min Act: -0.1700
Data Index: 47077 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1413. Min Range: -4.1413
Max Act: 4.0163. Min Act: -0.1700
Data Index: 1192463 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1413. Min Range: -4.1413
Max Act: 4.0163. Min Act: -0.1700
Data Index: 1189732 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1413. Min Range: -4.1413
Max Act: 4.0163. Min Act: -0.1700
Data Index: 650967 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1413. Min Range: -4.1413
Max Act: 4.0163. Min Act: -0.1700
Data Index: 225226 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1413. Min Range: -4.1413
Max Act: 4.0476. Min Act: -0.1700
Data Index: 964774 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1413. Min Range: -4.1413
Max Act: 4.0163. Min Act: -0.1700
Data Index: 269203 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1413. Min Range: -4.1413
Max Act: 3.9850. Min Act: -0.1700
Data Index: 1126626 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1413. Min Range: -4.1413
Max Act: 4.0163. Min Act: -0.1700
Data Index: 1103342 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1413. Min Range: -4.1413
Max Act: 3.9850. Min Act: -0.1700
Data Index: 415004 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1413. Min Range: -4.1413
Max Act: 3.9850. Min Act: -0.1700
Data Index: 1045786 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1413. Min Range: -4.1413
Max Act: 3.9850. Min Act: -0.1700
Data Index: 1234508 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1413. Min Range: -4.1413
Max Act: 3.9538. Min Act: -0.1700
Data Index: 525816 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1413. Min Range: -4.1413
Max Act: 3.9538. Min Act: -0.1700
Data Index: 323023 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1413. Min Range: -4.1413
Max Act: 3.9538. Min Act: -0.1700
Data Index: 284522 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1413. Min Range: -4.1413
Max Act: 3.9225. Min Act: -0.1700
Data Index: 422749 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1413. Min Range: -4.1413
Max Act: 3.9538. Min Act: -0.1700
Data Index: 1087795 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19