Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 62 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.5144. Min Act: -0.1700
Data Index: 407426 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.5144. Min Act: -0.1700
Data Index: 1167513 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.4206. Min Act: -0.1700
Data Index: 164541 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.4206. Min Act: -0.1700
Data Index: 1183282 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.3581. Min Act: -0.1700
Data Index: 71041 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.3581. Min Act: -0.1700
Data Index: 68264 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.3268. Min Act: -0.1700
Data Index: 657965 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.2956. Min Act: -0.1700
Data Index: 1165928 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.2956. Min Act: -0.1700
Data Index: 300917 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.2018. Min Act: -0.1700
Data Index: 1237346 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.2956. Min Act: -0.1700
Data Index: 304904 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.2331. Min Act: -0.1700
Data Index: 1198029 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.2018. Min Act: -0.1700
Data Index: 970305 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.2331. Min Act: -0.1700
Data Index: 1146071 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.1393. Min Act: -0.1700
Data Index: 660964 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.1393. Min Act: -0.1700
Data Index: 1130358 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.1393. Min Act: -0.1700
Data Index: 674592 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.1706. Min Act: -0.1700
Data Index: 686464 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.1393. Min Act: -0.1700
Data Index: 705302 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5144. Min Range: -4.5144
Max Act: 4.2018. Min Act: -0.1700
Data Index: 751028 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19