Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 142 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.7476. Min Act: -0.1700
Data Index: 1227652 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.7156. Min Act: -0.1700
Data Index: 1171893 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.6996. Min Act: -0.1700
Data Index: 494991 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.6516. Min Act: -0.1700
Data Index: 606090 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.6516. Min Act: -0.1700
Data Index: 928705 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.6194. Min Act: -0.1700
Data Index: 756041 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.6034. Min Act: -0.1700
Data Index: 1072170 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.5711. Min Act: -0.1700
Data Index: 779633 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.5873. Min Act: -0.1700
Data Index: 1197920 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.5711. Min Act: -0.1700
Data Index: 124607 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.5711. Min Act: -0.1700
Data Index: 167806 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.5711. Min Act: -0.1700
Data Index: 465105 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.5550. Min Act: -0.1700
Data Index: 1264102 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.5711. Min Act: -0.1700
Data Index: 918447 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.5711. Min Act: -0.1700
Data Index: 1117060 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.5711. Min Act: -0.1700
Data Index: 539240 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.5389. Min Act: -0.1700
Data Index: 1462014 (Python Code)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.5550. Min Act: -0.1700
Data Index: 804841 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.5389. Min Act: -0.1700
Data Index: 941846 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7476. Min Range: -2.7476
Max Act: 2.5550. Min Act: -0.1700
Data Index: 728770 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19