Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1815 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0700. Min Act: -0.1700
Data Index: 547377 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0384. Min Act: -0.1700
Data Index: 559879 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0542. Min Act: -0.1700
Data Index: 66365 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0384. Min Act: -0.1700
Data Index: 1175072 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0226. Min Act: -0.1700
Data Index: 46315 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0384. Min Act: -0.1700
Data Index: 1286195 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0226. Min Act: -0.1700
Data Index: 1351095 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0068. Min Act: -0.1700
Data Index: 1237810 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0068. Min Act: -0.1700
Data Index: 543746 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0226. Min Act: -0.1700
Data Index: 1055424 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0068. Min Act: -0.1700
Data Index: 144183 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0068. Min Act: -0.1700
Data Index: 1206555 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0068. Min Act: -0.1700
Data Index: 688303 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0068. Min Act: -0.1700
Data Index: 736875 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0068. Min Act: -0.1700
Data Index: 743975 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0068. Min Act: -0.1700
Data Index: 644253 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0068. Min Act: -0.1700
Data Index: 1265617 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0068. Min Act: -0.1700
Data Index: 1276766 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0068. Min Act: -0.1700
Data Index: 377268 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0700. Min Range: -3.0700
Max Act: 3.0068. Min Act: -0.1700
Data Index: 1299989 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19