Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1600 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.9013. Min Act: -0.1700
Data Index: 1629245 (Python Code)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.9325. Min Act: -0.1700
Data Index: 1521767 (Python Code)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.9013. Min Act: -0.1700
Data Index: 1393721 (Python Code)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.8856. Min Act: -0.1700
Data Index: 1502821 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.8700. Min Act: -0.1700
Data Index: 1419735 (Python Code)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.8856. Min Act: -0.1700
Data Index: 1585628 (Python Code)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.8388. Min Act: -0.1700
Data Index: 1632406 (Python Code)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.7919. Min Act: -0.1700
Data Index: 1496331 (Python Code)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.8075. Min Act: -0.1700
Data Index: 1398002 (Python Code)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.7763. Min Act: -0.1700
Data Index: 1656084 (Python Code)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.7606. Min Act: -0.1700
Data Index: 1562233 (Python Code)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.7138. Min Act: -0.1700
Data Index: 1544152 (Python Code)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.7606. Min Act: -0.1700
Data Index: 1634706 (Python Code)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.7450. Min Act: -0.1700
Data Index: 1570043 (Python Code)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.7450. Min Act: -0.1699
Data Index: 1454709 (Python Code)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.6981. Min Act: -0.1700
Data Index: 1567229 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.6981. Min Act: -0.1700
Data Index: 1409800 (Python Code)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.6825. Min Act: -0.1700
Data Index: 1492273 (Python Code)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.6669. Min Act: -0.1700
Data Index: 1560031 (Python Code)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9325. Min Range: -4.9325
Max Act: 4.6981. Min Act: -0.1700
Data Index: 1454713 (Python Code)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19