Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 14 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.9266. Min Act: -0.1700
Data Index: 341151 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.9107. Min Act: -0.1700
Data Index: 448158 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.8472. Min Act: -0.1700
Data Index: 117192 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.8472. Min Act: -0.1700
Data Index: 617009 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.8313. Min Act: -0.1700
Data Index: 472129 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.8154. Min Act: -0.1700
Data Index: 1226311 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.7995. Min Act: -0.1700
Data Index: 397270 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.7836. Min Act: -0.1700
Data Index: 1169210 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.7995. Min Act: -0.1700
Data Index: 428105 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.8313. Min Act: -0.1700
Data Index: 787797 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.7995. Min Act: -0.1700
Data Index: 598481 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.7676. Min Act: -0.1700
Data Index: 871989 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.7676. Min Act: -0.1700
Data Index: 471638 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.8154. Min Act: -0.1700
Data Index: 1084389 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.7836. Min Act: -0.1700
Data Index: 1328836 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.7836. Min Act: -0.1700
Data Index: 895358 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.7995. Min Act: -0.1700
Data Index: 1326409 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.7836. Min Act: -0.1700
Data Index: 1125389 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.7676. Min Act: -0.1700
Data Index: 1066499 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9266. Min Range: -2.9266
Max Act: 2.7836. Min Act: -0.1700
Data Index: 414221 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19