Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 471 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.6235. Min Act: -0.1700
Data Index: 54664 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.6074. Min Act: -0.1700
Data Index: 841540 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5913. Min Act: -0.1700
Data Index: 204142 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5752. Min Act: -0.1700
Data Index: 909295 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5430. Min Act: -0.1700
Data Index: 952650 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5430. Min Act: -0.1700
Data Index: 649215 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5591. Min Act: -0.1700
Data Index: 6961 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5268. Min Act: -0.1700
Data Index: 391703 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5430. Min Act: -0.1700
Data Index: 1117131 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5268. Min Act: -0.1700
Data Index: 196649 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5106. Min Act: -0.1700
Data Index: 559236 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5106. Min Act: -0.1700
Data Index: 434515 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.4944. Min Act: -0.1700
Data Index: 358596 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5106. Min Act: -0.1700
Data Index: 491914 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5106. Min Act: -0.1700
Data Index: 884212 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5106. Min Act: -0.1700
Data Index: 679654 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5106. Min Act: -0.1700
Data Index: 547155 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5106. Min Act: -0.1700
Data Index: 1335475 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.5106. Min Act: -0.1700
Data Index: 726577 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6235. Min Range: -2.6235
Max Act: 2.4944. Min Act: -0.1700
Data Index: 794624 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19