Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 784 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.8407. Min Act: -0.1700
Data Index: 493359 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.7782. Min Act: -0.1700
Data Index: 1296944 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.6532. Min Act: -0.1700
Data Index: 815945 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.5595. Min Act: -0.1700
Data Index: 1253597 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.5595. Min Act: -0.1700
Data Index: 901481 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.4970. Min Act: -0.1700
Data Index: 950730 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.4032. Min Act: -0.1700
Data Index: 102443 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.3720. Min Act: -0.1700
Data Index: 1065224 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.3094. Min Act: -0.1700
Data Index: 796233 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.2157. Min Act: -0.1700
Data Index: 680777 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.2157. Min Act: -0.1700
Data Index: 1281586 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.2157. Min Act: -0.1700
Data Index: 464198 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.2157. Min Act: -0.1700
Data Index: 1146798 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.1532. Min Act: -0.1700
Data Index: 1340867 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.2157. Min Act: -0.1700
Data Index: 1109238 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.1219. Min Act: -0.1700
Data Index: 826475 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.0906. Min Act: -0.1700
Data Index: 165924 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.0906. Min Act: -0.1700
Data Index: 206064 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.0594. Min Act: -0.1700
Data Index: 445587 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8407. Min Range: -4.8407
Max Act: 4.0594. Min Act: -0.1700
Data Index: 939597 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19