Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1950 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1559. Min Range: -4.1559
Max Act: 4.1559. Min Act: -0.1700
Data Index: 959236 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1559. Min Range: -4.1559
Max Act: 4.0933. Min Act: -0.1700
Data Index: 324278 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1559. Min Range: -4.1559
Max Act: 4.0621. Min Act: -0.1700
Data Index: 260521 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.9996. Min Act: -0.1699
Data Index: 1328173 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.9370. Min Act: -0.1700
Data Index: 65205 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.9058. Min Act: -0.1700
Data Index: 1080229 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.9058. Min Act: -0.1700
Data Index: 304826 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.9058. Min Act: -0.1700
Data Index: 857694 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.8745. Min Act: -0.1700
Data Index: 221032 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.8432. Min Act: -0.1700
Data Index: 206351 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.8432. Min Act: -0.1700
Data Index: 1199291 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.8119. Min Act: -0.1700
Data Index: 1232283 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.8432. Min Act: -0.1700
Data Index: 1342951 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.8119. Min Act: -0.1700
Data Index: 44529 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.8432. Min Act: -0.1700
Data Index: 1138929 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.8119. Min Act: -0.1700
Data Index: 1537092 (Python Code)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.7806. Min Act: -0.1700
Data Index: 219977 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.8119. Min Act: -0.1700
Data Index: 961717 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.8119. Min Act: -0.1700
Data Index: 880926 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1559. Min Range: -4.1559
Max Act: 3.8119. Min Act: -0.1700
Data Index: 562080 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19