Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 55 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.1398. Min Act: -0.1700
Data Index: 763985 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.1398. Min Act: -0.1700
Data Index: 1146465 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.1085. Min Act: -0.1700
Data Index: 230660 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0460. Min Act: -0.1700
Data Index: 781327 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0460. Min Act: -0.1700
Data Index: 786147 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0773. Min Act: -0.1700
Data Index: 121177 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0773. Min Act: -0.1700
Data Index: 300223 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0460. Min Act: -0.1700
Data Index: 51780 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0460. Min Act: -0.1700
Data Index: 860169 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0460. Min Act: -0.1700
Data Index: 898121 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0148. Min Act: -0.1700
Data Index: 1173661 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0304. Min Act: -0.1700
Data Index: 1067565 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0148. Min Act: -0.1700
Data Index: 415634 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1398. Min Range: -4.1398
Max Act: 3.9991. Min Act: -0.1700
Data Index: 406160 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0304. Min Act: -0.1700
Data Index: 116788 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0304. Min Act: -0.1700
Data Index: 794174 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0460. Min Act: -0.1700
Data Index: 1240806 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0304. Min Act: -0.1700
Data Index: 669066 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0148. Min Act: -0.1700
Data Index: 704170 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1398. Min Range: -4.1398
Max Act: 4.0148. Min Act: -0.1700
Data Index: 13958 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19