Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1996 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.2994. Min Act: -0.1700
Data Index: 127312 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.2369. Min Act: -0.1700
Data Index: 196677 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.1744. Min Act: -0.1700
Data Index: 776896 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.2056. Min Act: -0.1700
Data Index: 1336179 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.2369. Min Act: -0.1700
Data Index: 26396 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.1119. Min Act: -0.1700
Data Index: 728135 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.0494. Min Act: -0.1700
Data Index: 79277 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.0494. Min Act: -0.1700
Data Index: 699631 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.0494. Min Act: -0.1700
Data Index: 271197 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.0806. Min Act: -0.1700
Data Index: 280952 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.1119. Min Act: -0.1700
Data Index: 1246213 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.0806. Min Act: -0.1700
Data Index: 1078059 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.0806. Min Act: -0.1700
Data Index: 90675 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.1119. Min Act: -0.1700
Data Index: 651904 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2994. Min Range: -5.2994
Max Act: 4.9556. Min Act: -0.1700
Data Index: 526094 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.0494. Min Act: -0.1700
Data Index: 784159 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2994. Min Range: -5.2994
Max Act: 4.9869. Min Act: -0.1700
Data Index: 219116 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.0181. Min Act: -0.1700
Data Index: 1152387 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2994. Min Range: -5.2994
Max Act: 5.0806. Min Act: -0.1700
Data Index: 893707 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2994. Min Range: -5.2994
Max Act: 4.8931. Min Act: -0.1700
Data Index: 203365 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19