Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 41 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.8287. Min Act: -0.1700
Data Index: 660952 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.7809. Min Act: -0.1700
Data Index: 539809 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.7331. Min Act: -0.1700
Data Index: 866339 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.7171. Min Act: -0.1700
Data Index: 1555380 (Python Code)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.7171. Min Act: -0.1700
Data Index: 1443911 (Python Code)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6851. Min Act: -0.1700
Data Index: 1468357 (Python Code)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6851. Min Act: -0.1700
Data Index: 1423584 (Python Code)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6691. Min Act: -0.1700
Data Index: 1374620 (Python Code)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6530. Min Act: -0.1700
Data Index: 1387700 (Python Code)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6530. Min Act: -0.1700
Data Index: 1512313 (Python Code)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6530. Min Act: -0.1700
Data Index: 1334102 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6370. Min Act: -0.1700
Data Index: 884749 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6370. Min Act: -0.1700
Data Index: 428041 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6370. Min Act: -0.1700
Data Index: 1424365 (Python Code)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6370. Min Act: -0.1700
Data Index: 1463961 (Python Code)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6370. Min Act: -0.1700
Data Index: 1383493 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6370. Min Act: -0.1700
Data Index: 1625716 (Python Code)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6209. Min Act: -0.1700
Data Index: 1283068 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6209. Min Act: -0.1700
Data Index: 1618174 (Python Code)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8287. Min Range: -2.8287
Max Act: 2.6209. Min Act: -0.1700
Data Index: 1510906 (Python Code)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19