Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 125 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1453. Min Range: -3.1453
Max Act: 3.1453. Min Act: -0.1700
Data Index: 610066 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1453. Min Range: -3.1453
Max Act: 3.1138. Min Act: -0.1700
Data Index: 547365 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1453. Min Range: -3.1453
Max Act: 3.0980. Min Act: -0.1700
Data Index: 777319 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1453. Min Range: -3.1453
Max Act: 3.0507. Min Act: -0.1700
Data Index: 1234992 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1453. Min Range: -3.1453
Max Act: 3.0191. Min Act: -0.1700
Data Index: 1314725 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1453. Min Range: -3.1453
Max Act: 3.0191. Min Act: -0.1700
Data Index: 842861 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1453. Min Range: -3.1453
Max Act: 3.0507. Min Act: -0.1700
Data Index: 116856 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1453. Min Range: -3.1453
Max Act: 3.0191. Min Act: -0.1700
Data Index: 7860 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1453. Min Range: -3.1453
Max Act: 3.0191. Min Act: -0.1700
Data Index: 572161 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1453. Min Range: -3.1453
Max Act: 2.9558. Min Act: -0.1700
Data Index: 920591 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1453. Min Range: -3.1453
Max Act: 2.9716. Min Act: -0.1700
Data Index: 441689 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1453. Min Range: -3.1453
Max Act: 2.9241. Min Act: -0.1700
Data Index: 904047 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1453. Min Range: -3.1453
Max Act: 2.9241. Min Act: -0.1700
Data Index: 1109419 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1453. Min Range: -3.1453
Max Act: 2.9558. Min Act: -0.1700
Data Index: 244487 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1453. Min Range: -3.1453
Max Act: 2.9241. Min Act: -0.1700
Data Index: 803933 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1453. Min Range: -3.1453
Max Act: 2.9716. Min Act: -0.1700
Data Index: 1105045 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1453. Min Range: -3.1453
Max Act: 2.9558. Min Act: -0.1700
Data Index: 965163 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1453. Min Range: -3.1453
Max Act: 2.9083. Min Act: -0.1700
Data Index: 1039678 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1453. Min Range: -3.1453
Max Act: 2.9241. Min Act: -0.1700
Data Index: 1218675 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1453. Min Range: -3.1453
Max Act: 2.8766. Min Act: -0.1700
Data Index: 557107 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19