Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 132 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1161. Min Range: -3.1161
Max Act: 3.1161. Min Act: -0.1700
Data Index: 857945 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1161. Min Range: -3.1161
Max Act: 3.0214. Min Act: -0.1700
Data Index: 294856 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1161. Min Range: -3.1161
Max Act: 3.0372. Min Act: -0.1700
Data Index: 661373 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1161. Min Range: -3.1161
Max Act: 3.0056. Min Act: -0.1700
Data Index: 94901 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9898. Min Act: -0.1700
Data Index: 444852 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1161. Min Range: -3.1161
Max Act: 3.0214. Min Act: -0.1700
Data Index: 1026135 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9898. Min Act: -0.1700
Data Index: 297974 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9582. Min Act: -0.1700
Data Index: 240524 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9740. Min Act: -0.1700
Data Index: 774995 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9582. Min Act: -0.1700
Data Index: 1046756 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9423. Min Act: -0.1700
Data Index: 844875 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9740. Min Act: -0.1700
Data Index: 506214 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9423. Min Act: -0.1700
Data Index: 802679 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9582. Min Act: -0.1700
Data Index: 976863 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9898. Min Act: -0.1700
Data Index: 793198 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9740. Min Act: -0.1700
Data Index: 29385 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9423. Min Act: -0.1700
Data Index: 565314 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9423. Min Act: -0.1700
Data Index: 119369 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.8948. Min Act: -0.1700
Data Index: 678488 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1161. Min Range: -3.1161
Max Act: 2.9423. Min Act: -0.1700
Data Index: 109403 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19