Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 0 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.8270. Min Act: -0.1700
Data Index: 1029971 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.8114. Min Act: -0.1700
Data Index: 169774 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.7957. Min Act: -0.1700
Data Index: 1278056 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.8270. Min Act: -0.1700
Data Index: 895385 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.7332. Min Act: -0.1700
Data Index: 515607 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.7020. Min Act: -0.1700
Data Index: 689795 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.7332. Min Act: -0.1700
Data Index: 342118 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.6395. Min Act: -0.1700
Data Index: 149675 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.6551. Min Act: -0.1700
Data Index: 1326453 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.5926. Min Act: -0.1700
Data Index: 796238 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.6395. Min Act: -0.1700
Data Index: 589407 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.6239. Min Act: -0.1700
Data Index: 249846 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.6239. Min Act: -0.1699
Data Index: 768831 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.6395. Min Act: -0.1700
Data Index: 1309237 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.6082. Min Act: -0.1700
Data Index: 893584 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.6395. Min Act: -0.1700
Data Index: 146537 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.6395. Min Act: -0.1700
Data Index: 1321033 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.5770. Min Act: -0.1700
Data Index: 565389 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.5301. Min Act: -0.1700
Data Index: 1017113 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8270. Min Range: -4.8270
Max Act: 4.5457. Min Act: -0.1700
Data Index: 89091 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19