Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1559 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.0623. Min Range: -4.0623
Max Act: 4.0623. Min Act: -0.1700
Data Index: 1353591 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0623. Min Range: -4.0623
Max Act: 4.0310. Min Act: -0.1700
Data Index: 130709 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9998. Min Act: -0.1700
Data Index: 693238 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0623. Min Range: -4.0623
Max Act: 4.0310. Min Act: -0.1700
Data Index: 264580 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9685. Min Act: -0.1700
Data Index: 138253 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0623. Min Range: -4.0623
Max Act: 4.0310. Min Act: -0.1700
Data Index: 346835 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9685. Min Act: -0.1700
Data Index: 631306 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9059. Min Act: -0.1700
Data Index: 707076 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9685. Min Act: -0.1700
Data Index: 183758 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9685. Min Act: -0.1700
Data Index: 3883 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9372. Min Act: -0.1700
Data Index: 636064 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9059. Min Act: -0.1700
Data Index: 52445 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9059. Min Act: -0.1700
Data Index: 147019 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8747. Min Act: -0.1700
Data Index: 1434014 (Python Code)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9685. Min Act: -0.1700
Data Index: 1544855 (Python Code)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9059. Min Act: -0.1700
Data Index: 1508102 (Python Code)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8747. Min Act: -0.1700
Data Index: 623139 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8747. Min Act: -0.1700
Data Index: 713157 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9059. Min Act: -0.1700
Data Index: 1216880 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9059. Min Act: -0.1700
Data Index: 1054384 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19