Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 20 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.2643. Min Range: -5.2643
Max Act: 5.2643. Min Act: -0.1700
Data Index: 1189002 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2643. Min Range: -5.2643
Max Act: 5.1080. Min Act: -0.1700
Data Index: 678245 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.9518. Min Act: -0.1700
Data Index: 773129 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.8580. Min Act: -0.1700
Data Index: 476490 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.8580. Min Act: -0.1700
Data Index: 1018591 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.7799. Min Act: -0.1700
Data Index: 45460 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.7955. Min Act: -0.1700
Data Index: 1062353 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.7330. Min Act: -0.1700
Data Index: 961286 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.7487. Min Act: -0.1700
Data Index: 154661 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.7487. Min Act: -0.1700
Data Index: 1031475 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.7174. Min Act: -0.1700
Data Index: 853068 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.7174. Min Act: -0.1700
Data Index: 1074184 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.7330. Min Act: -0.1700
Data Index: 410261 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.7174. Min Act: -0.1700
Data Index: 990713 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.7018. Min Act: -0.1700
Data Index: 1107585 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.6705. Min Act: -0.1700
Data Index: 1002664 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.7330. Min Act: -0.1700
Data Index: 390010 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.6705. Min Act: -0.1700
Data Index: 662234 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.6862. Min Act: -0.1700
Data Index: 1007763 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2643. Min Range: -5.2643
Max Act: 4.7174. Min Act: -0.1700
Data Index: 1078305 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19