Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2040 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.9134. Min Act: -0.1700
Data Index: 394351 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.8975. Min Act: -0.1700
Data Index: 955206 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.8817. Min Act: -0.1700
Data Index: 444744 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.8499. Min Act: -0.1700
Data Index: 78269 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.8181. Min Act: -0.1700
Data Index: 1007730 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7862. Min Act: -0.1700
Data Index: 164293 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7862. Min Act: -0.1700
Data Index: 390855 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7703. Min Act: -0.1700
Data Index: 729680 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7384. Min Act: -0.1700
Data Index: 1075752 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7703. Min Act: -0.1700
Data Index: 285473 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7544. Min Act: -0.1700
Data Index: 1138835 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7544. Min Act: -0.1700
Data Index: 323608 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7224. Min Act: -0.1700
Data Index: 589558 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7544. Min Act: -0.1700
Data Index: 569192 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7384. Min Act: -0.1700
Data Index: 132727 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7224. Min Act: -0.1700
Data Index: 20250 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7384. Min Act: -0.1700
Data Index: 97011 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7384. Min Act: -0.1700
Data Index: 318255 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7384. Min Act: -0.1700
Data Index: 829401 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9134. Min Range: -2.9134
Max Act: 2.7384. Min Act: -0.1700
Data Index: 737802 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19