Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 307 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2085. Min Range: -4.2085
Max Act: 4.2085. Min Act: -0.1700
Data Index: 246369 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2085. Min Range: -4.2085
Max Act: 4.1773. Min Act: -0.1700
Data Index: 457637 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2085. Min Range: -4.2085
Max Act: 4.0835. Min Act: -0.1700
Data Index: 1333296 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2085. Min Range: -4.2085
Max Act: 4.0835. Min Act: -0.1700
Data Index: 747977 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2085. Min Range: -4.2085
Max Act: 4.0522. Min Act: -0.1699
Data Index: 654901 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2085. Min Range: -4.2085
Max Act: 4.0522. Min Act: -0.1700
Data Index: 349346 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2085. Min Range: -4.2085
Max Act: 3.9584. Min Act: -0.1700
Data Index: 873144 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2085. Min Range: -4.2085
Max Act: 4.0210. Min Act: -0.1700
Data Index: 1351776 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2085. Min Range: -4.2085
Max Act: 3.9897. Min Act: -0.1700
Data Index: 1016624 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2085. Min Range: -4.2085
Max Act: 3.9897. Min Act: -0.1700
Data Index: 1065726 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2085. Min Range: -4.2085
Max Act: 4.0210. Min Act: -0.1699
Data Index: 1078073 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2085. Min Range: -4.2085
Max Act: 3.9897. Min Act: -0.1700
Data Index: 108311 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2085. Min Range: -4.2085
Max Act: 3.9897. Min Act: -0.1700
Data Index: 582592 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2085. Min Range: -4.2085
Max Act: 4.0210. Min Act: -0.1699
Data Index: 287426 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2085. Min Range: -4.2085
Max Act: 3.9897. Min Act: -0.1700
Data Index: 1097169 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2085. Min Range: -4.2085
Max Act: 3.9584. Min Act: -0.1700
Data Index: 415958 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2085. Min Range: -4.2085
Max Act: 3.9584. Min Act: -0.1700
Data Index: 691114 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2085. Min Range: -4.2085
Max Act: 3.9584. Min Act: -0.1700
Data Index: 172314 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2085. Min Range: -4.2085
Max Act: 3.9271. Min Act: -0.1700
Data Index: 278177 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2085. Min Range: -4.2085
Max Act: 3.9584. Min Act: -0.1700
Data Index: 477056 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19