Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1488 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.7999. Min Act: -0.1700
Data Index: 939468 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.8158. Min Act: -0.1700
Data Index: 1447833 (Python Code)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.7999. Min Act: -0.1700
Data Index: 11067 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.7999. Min Act: -0.1700
Data Index: 1314411 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.7520. Min Act: -0.1700
Data Index: 1036310 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.7680. Min Act: -0.1700
Data Index: 668092 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.7361. Min Act: -0.1700
Data Index: 434061 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.7201. Min Act: -0.1700
Data Index: 597760 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.7201. Min Act: -0.1700
Data Index: 1146548 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.7201. Min Act: -0.1700
Data Index: 545278 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.7041. Min Act: -0.1700
Data Index: 785377 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.7041. Min Act: -0.1700
Data Index: 483210 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.7201. Min Act: -0.1700
Data Index: 474727 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.6881. Min Act: -0.1700
Data Index: 965163 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.6881. Min Act: -0.1700
Data Index: 1046781 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.6721. Min Act: -0.1700
Data Index: 876490 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.6881. Min Act: -0.1700
Data Index: 1262160 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.6721. Min Act: -0.1700
Data Index: 1508486 (Python Code)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.6560. Min Act: -0.1700
Data Index: 1310168 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8158. Min Range: -2.8158
Max Act: 2.6560. Min Act: -0.1700
Data Index: 674896 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19