Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1335 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.6757. Min Act: -0.1700
Data Index: 1477373 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.6757. Min Act: -0.1700
Data Index: 1461276 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.6132. Min Act: -0.1700
Data Index: 1361031 (Python Code)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.5819. Min Act: -0.1700
Data Index: 1366554 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.5819. Min Act: -0.1700
Data Index: 1565286 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.4882. Min Act: -0.1700
Data Index: 1396320 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.4882. Min Act: -0.1700
Data Index: 1495340 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.4882. Min Act: -0.1700
Data Index: 1514986 (Python Code)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.3631. Min Act: -0.1700
Data Index: 1556781 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.3944. Min Act: -0.1700
Data Index: 1516887 (Python Code)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.3944. Min Act: -0.1700
Data Index: 1530187 (Python Code)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.3319. Min Act: -0.1700
Data Index: 1393860 (Python Code)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.3631. Min Act: -0.1700
Data Index: 1586028 (Python Code)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.3944. Min Act: -0.1700
Data Index: 1374814 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.3631. Min Act: -0.1700
Data Index: 1489826 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.3631. Min Act: -0.1700
Data Index: 1453754 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.3319. Min Act: -0.1700
Data Index: 1430623 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.3319. Min Act: -0.1700
Data Index: 1475256 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.2694. Min Act: -0.1700
Data Index: 1385960 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6757. Min Range: -4.6757
Max Act: 4.3006. Min Act: -0.1700
Data Index: 1526300 (Python Code)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19