Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1498 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.7846. Min Act: -0.1700
Data Index: 784730 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.7533. Min Act: -0.1700
Data Index: 1054272 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.7221. Min Act: -0.1700
Data Index: 1007903 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5971. Min Act: -0.1700
Data Index: 25665 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5346. Min Act: -0.1700
Data Index: 596950 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5658. Min Act: -0.1700
Data Index: 1102657 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5346. Min Act: -0.1700
Data Index: 981568 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5346. Min Act: -0.1700
Data Index: 1280030 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5033. Min Act: -0.1700
Data Index: 1049523 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5033. Min Act: -0.1700
Data Index: 1044719 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5033. Min Act: -0.1700
Data Index: 1273331 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5033. Min Act: -0.1700
Data Index: 644863 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5033. Min Act: -0.1700
Data Index: 714749 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5033. Min Act: -0.1700
Data Index: 214690 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5033. Min Act: -0.1700
Data Index: 1106850 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.4408. Min Act: -0.1700
Data Index: 161207 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.4408. Min Act: -0.1700
Data Index: 718042 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5033. Min Act: -0.1700
Data Index: 1060292 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.4720. Min Act: -0.1700
Data Index: 892149 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7846. Min Range: -4.7846
Max Act: 4.5033. Min Act: -0.1700
Data Index: 260860 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19