Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 295 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0158. Min Range: -4.0158
Max Act: 4.0158. Min Act: -0.1700
Data Index: 706677 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.9846. Min Act: -0.1700
Data Index: 133129 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.9533. Min Act: -0.1700
Data Index: 803416 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.9220. Min Act: -0.1700
Data Index: 1436030 (Python Code)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.8908. Min Act: -0.1700
Data Index: 741282 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.8908. Min Act: -0.1700
Data Index: 969523 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.8282. Min Act: -0.1700
Data Index: 351100 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.8908. Min Act: -0.1698
Data Index: 1509322 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.8751. Min Act: -0.1700
Data Index: 1080993 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.8595. Min Act: -0.1700
Data Index: 1451194 (Python Code)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.8595. Min Act: -0.1700
Data Index: 1224058 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.8282. Min Act: -0.1700
Data Index: 1283646 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.8282. Min Act: -0.1700
Data Index: 1068268 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.8126. Min Act: -0.1700
Data Index: 638328 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.7969. Min Act: -0.1700
Data Index: 351829 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.7813. Min Act: -0.1700
Data Index: 456618 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.8126. Min Act: -0.1700
Data Index: 548669 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.7969. Min Act: -0.1700
Data Index: 1065942 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.8126. Min Act: -0.1700
Data Index: 1396695 (Python Code)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0158. Min Range: -4.0158
Max Act: 3.7500. Min Act: -0.1700
Data Index: 83923 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19