Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2011 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2457. Min Range: -4.2457
Max Act: 4.2457. Min Act: -0.1700
Data Index: 662565 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2457. Min Range: -4.2457
Max Act: 4.1988. Min Act: -0.1700
Data Index: 287736 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2457. Min Range: -4.2457
Max Act: 4.1520. Min Act: -0.1700
Data Index: 991423 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2457. Min Range: -4.2457
Max Act: 4.1363. Min Act: -0.1700
Data Index: 404073 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2457. Min Range: -4.2457
Max Act: 4.0425. Min Act: -0.1700
Data Index: 91007 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2457. Min Range: -4.2457
Max Act: 4.0425. Min Act: -0.1700
Data Index: 1228819 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2457. Min Range: -4.2457
Max Act: 4.0425. Min Act: -0.1700
Data Index: 524309 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2457. Min Range: -4.2457
Max Act: 4.0269. Min Act: -0.1700
Data Index: 1221532 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2457. Min Range: -4.2457
Max Act: 4.0582. Min Act: -0.1700
Data Index: 1170817 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2457. Min Range: -4.2457
Max Act: 4.0425. Min Act: -0.1700
Data Index: 965055 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2457. Min Range: -4.2457
Max Act: 4.0113. Min Act: -0.1700
Data Index: 889260 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2457. Min Range: -4.2457
Max Act: 3.9956. Min Act: -0.1700
Data Index: 876399 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2457. Min Range: -4.2457
Max Act: 4.0269. Min Act: -0.1700
Data Index: 815454 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2457. Min Range: -4.2457
Max Act: 3.9331. Min Act: -0.1700
Data Index: 444878 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2457. Min Range: -4.2457
Max Act: 3.9487. Min Act: -0.1700
Data Index: 1338873 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2457. Min Range: -4.2457
Max Act: 3.9487. Min Act: -0.1700
Data Index: 1153239 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2457. Min Range: -4.2457
Max Act: 3.9487. Min Act: -0.1700
Data Index: 379738 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2457. Min Range: -4.2457
Max Act: 3.9331. Min Act: -0.1700
Data Index: 214224 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2457. Min Range: -4.2457
Max Act: 3.9175. Min Act: -0.1700
Data Index: 1175046 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2457. Min Range: -4.2457
Max Act: 3.9175. Min Act: -0.1700
Data Index: 80803 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19