Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 195 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7817. Min Act: -0.1700
Data Index: 358675 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7658. Min Act: -0.1700
Data Index: 126813 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7658. Min Act: -0.1700
Data Index: 729410 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7339. Min Act: -0.1700
Data Index: 1307098 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7498. Min Act: -0.1700
Data Index: 377135 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7339. Min Act: -0.1700
Data Index: 252413 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7339. Min Act: -0.1700
Data Index: 263480 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7339. Min Act: -0.1700
Data Index: 1293059 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7179. Min Act: -0.1700
Data Index: 1314989 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7019. Min Act: -0.1700
Data Index: 730807 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7019. Min Act: -0.1700
Data Index: 315588 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7019. Min Act: -0.1700
Data Index: 220604 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7019. Min Act: -0.1700
Data Index: 594772 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.6859. Min Act: -0.1700
Data Index: 281703 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.7019. Min Act: -0.1700
Data Index: 1324410 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.6859. Min Act: -0.1700
Data Index: 1049640 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.6859. Min Act: -0.1700
Data Index: 74835 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.6859. Min Act: -0.1700
Data Index: 147230 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.6859. Min Act: -0.1700
Data Index: 256154 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7817. Min Range: -2.7817
Max Act: 2.6859. Min Act: -0.1700
Data Index: 1163037 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19