Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 81 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.4832. Min Act: -0.1700
Data Index: 374855 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.4670. Min Act: -0.1700
Data Index: 533494 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.4670. Min Act: -0.1700
Data Index: 175271 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.4507. Min Act: -0.1700
Data Index: 699025 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.4507. Min Act: -0.1699
Data Index: 50912 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.4345. Min Act: -0.1700
Data Index: 912093 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.4345. Min Act: -0.1700
Data Index: 895375 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.4182. Min Act: -0.1700
Data Index: 481116 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.4019. Min Act: -0.1700
Data Index: 1306164 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.3856. Min Act: -0.1700
Data Index: 682236 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.4019. Min Act: -0.1700
Data Index: 1109514 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.4019. Min Act: -0.1700
Data Index: 464354 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.3856. Min Act: -0.1700
Data Index: 544158 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.3856. Min Act: -0.1700
Data Index: 358646 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.3856. Min Act: -0.1700
Data Index: 1265419 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.3692. Min Act: -0.1700
Data Index: 260125 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.3856. Min Act: -0.1700
Data Index: 622404 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.3692. Min Act: -0.1700
Data Index: 93716 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.3856. Min Act: -0.1700
Data Index: 827351 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4832. Min Range: -2.4832
Max Act: 2.3692. Min Act: -0.1700
Data Index: 260585 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19