Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 22 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.7134. Min Act: -0.1700
Data Index: 1054494 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6814. Min Act: -0.1699
Data Index: 105874 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6814. Min Act: -0.1700
Data Index: 1286302 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6814. Min Act: -0.1699
Data Index: 166182 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6814. Min Act: -0.1700
Data Index: 96232 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6974. Min Act: -0.1700
Data Index: 626425 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6654. Min Act: -0.1700
Data Index: 960259 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6654. Min Act: -0.1699
Data Index: 503325 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6493. Min Act: -0.1700
Data Index: 346824 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6493. Min Act: -0.1700
Data Index: 626177 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6493. Min Act: -0.1700
Data Index: 1155844 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6493. Min Act: -0.1698
Data Index: 148983 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6493. Min Act: -0.1700
Data Index: 925484 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6493. Min Act: -0.1700
Data Index: 233832 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6333. Min Act: -0.1700
Data Index: 1261124 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6333. Min Act: -0.1700
Data Index: 1300560 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6172. Min Act: -0.1699
Data Index: 342036 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6333. Min Act: -0.1700
Data Index: 925030 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6333. Min Act: -0.1700
Data Index: 1077175 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7134. Min Range: -2.7134
Max Act: 2.6333. Min Act: -0.1700
Data Index: 591307 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19