Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1013 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1587. Min Range: -3.1587
Max Act: 3.1587. Min Act: -0.1700
Data Index: 414129 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1587. Min Range: -3.1587
Max Act: 3.0325. Min Act: -0.1700
Data Index: 279782 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1587. Min Range: -3.1587
Max Act: 3.0167. Min Act: -0.1700
Data Index: 878967 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1587. Min Range: -3.1587
Max Act: 3.0009. Min Act: -0.1700
Data Index: 1269884 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.9693. Min Act: -0.1700
Data Index: 413360 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.9693. Min Act: -0.1700
Data Index: 835923 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.9535. Min Act: -0.1700
Data Index: 559959 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.9535. Min Act: -0.1700
Data Index: 696451 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.9376. Min Act: -0.1700
Data Index: 73379 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.9535. Min Act: -0.1700
Data Index: 1160446 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.9535. Min Act: -0.1700
Data Index: 274183 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.9218. Min Act: -0.1700
Data Index: 1218781 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.9218. Min Act: -0.1700
Data Index: 702157 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.9218. Min Act: -0.1700
Data Index: 1180998 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.8901. Min Act: -0.1700
Data Index: 1335386 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.8583. Min Act: -0.1700
Data Index: 1329074 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.8742. Min Act: -0.1700
Data Index: 1217565 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.8583. Min Act: -0.1700
Data Index: 639294 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.8583. Min Act: -0.1700
Data Index: 416400 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1587. Min Range: -3.1587
Max Act: 2.8583. Min Act: -0.1700
Data Index: 821485 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19