Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 71 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1846. Min Act: -0.1700
Data Index: 466293 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1846. Min Act: -0.1700
Data Index: 1286546 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1680. Min Act: -0.1700
Data Index: 977518 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1680. Min Act: -0.1700
Data Index: 1093515 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1347. Min Act: -0.1700
Data Index: 172402 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1180. Min Act: -0.1700
Data Index: 424056 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1013. Min Act: -0.1700
Data Index: 892755 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1347. Min Act: -0.1700
Data Index: 95683 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1180. Min Act: -0.1700
Data Index: 962015 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1180. Min Act: -0.1700
Data Index: 1165695 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1013. Min Act: -0.1700
Data Index: 1593251 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1013. Min Act: -0.1700
Data Index: 1647025 (Python Code)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1180. Min Act: -0.1700
Data Index: 928729 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1347. Min Act: -0.1700
Data Index: 675688 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.0846. Min Act: -0.1700
Data Index: 299051 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1013. Min Act: -0.1700
Data Index: 1181230 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1013. Min Act: -0.1700
Data Index: 1332609 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1013. Min Act: -0.1700
Data Index: 1185218 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.1013. Min Act: -0.1700
Data Index: 413771 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1846. Min Range: -2.1846
Max Act: 2.0846. Min Act: -0.1700
Data Index: 28367 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19