Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 48 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.5400. Min Act: -0.1700
Data Index: 90702 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.5244. Min Act: -0.1700
Data Index: 280474 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.5087. Min Act: -0.1700
Data Index: 526342 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.4773. Min Act: -0.1700
Data Index: 766481 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.4773. Min Act: -0.1700
Data Index: 1168648 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.4617. Min Act: -0.1700
Data Index: 443273 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.4460. Min Act: -0.1700
Data Index: 1068871 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.4303. Min Act: -0.1700
Data Index: 1007994 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.4460. Min Act: -0.1700
Data Index: 919948 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.4146. Min Act: -0.1700
Data Index: 253502 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.4303. Min Act: -0.1700
Data Index: 987916 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.4303. Min Act: -0.1700
Data Index: 1349659 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.3990. Min Act: -0.1700
Data Index: 1226189 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.3676. Min Act: -0.1700
Data Index: 849006 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.4146. Min Act: -0.1700
Data Index: 1046407 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.3676. Min Act: -0.1700
Data Index: 66008 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.3676. Min Act: -0.1700
Data Index: 1196008 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.3362. Min Act: -0.1700
Data Index: 169314 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.3990. Min Act: -0.1700
Data Index: 1131292 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5400. Min Range: -3.5400
Max Act: 3.4146. Min Act: -0.1700
Data Index: 1085496 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19