Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 249 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0241. Min Range: -3.0241
Max Act: 3.0241. Min Act: -0.1700
Data Index: 289542 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0241. Min Range: -3.0241
Max Act: 3.0083. Min Act: -0.1700
Data Index: 1592248 (Python Code)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9767. Min Act: -0.1700
Data Index: 470880 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9767. Min Act: -0.1700
Data Index: 1080878 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9450. Min Act: -0.1700
Data Index: 225126 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9608. Min Act: -0.1700
Data Index: 1051084 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9450. Min Act: -0.1700
Data Index: 416658 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9608. Min Act: -0.1700
Data Index: 652794 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9292. Min Act: -0.1700
Data Index: 726459 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9608. Min Act: -0.1700
Data Index: 672329 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9292. Min Act: -0.1700
Data Index: 1110153 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9608. Min Act: -0.1700
Data Index: 697482 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9450. Min Act: -0.1700
Data Index: 1275700 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9608. Min Act: -0.1700
Data Index: 595292 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9292. Min Act: -0.1700
Data Index: 832813 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9292. Min Act: -0.1700
Data Index: 595691 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9450. Min Act: -0.1700
Data Index: 922832 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9450. Min Act: -0.1700
Data Index: 18607 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9450. Min Act: -0.1700
Data Index: 233259 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0241. Min Range: -3.0241
Max Act: 2.9450. Min Act: -0.1700
Data Index: 1083367 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19