Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1740 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.3525. Min Act: -0.1700
Data Index: 831761 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.2425. Min Act: -0.1700
Data Index: 777977 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.1954. Min Act: -0.1700
Data Index: 1067301 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.1481. Min Act: -0.1700
Data Index: 1210365 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.1639. Min Act: -0.1700
Data Index: 185623 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.1481. Min Act: -0.1700
Data Index: 738826 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.1324. Min Act: -0.1700
Data Index: 1332295 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.1166. Min Act: -0.1700
Data Index: 112018 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.0693. Min Act: -0.1700
Data Index: 1066235 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.1009. Min Act: -0.1700
Data Index: 182702 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.0851. Min Act: -0.1700
Data Index: 10324 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.1009. Min Act: -0.1700
Data Index: 1101528 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.1009. Min Act: -0.1700
Data Index: 57197 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.0693. Min Act: -0.1700
Data Index: 922498 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.0377. Min Act: -0.1700
Data Index: 428858 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.0851. Min Act: -0.1700
Data Index: 1319780 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.0535. Min Act: -0.1700
Data Index: 382200 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.0377. Min Act: -0.1700
Data Index: 267339 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.0219. Min Act: -0.1700
Data Index: 1260053 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3525. Min Range: -3.3525
Max Act: 3.0377. Min Act: -0.1700
Data Index: 417953 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19