Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1951 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.8944. Min Act: -0.1700
Data Index: 849873 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.8149. Min Act: -0.1700
Data Index: 452002 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7990. Min Act: -0.1700
Data Index: 341912 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7990. Min Act: -0.1700
Data Index: 46793 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7990. Min Act: -0.1700
Data Index: 453698 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7831. Min Act: -0.1700
Data Index: 989640 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7671. Min Act: -0.1700
Data Index: 1520372 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7512. Min Act: -0.1700
Data Index: 267477 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7352. Min Act: -0.1700
Data Index: 1072050 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7352. Min Act: -0.1700
Data Index: 1432692 (Python Code)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7512. Min Act: -0.1700
Data Index: 1499204 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7192. Min Act: -0.1700
Data Index: 420990 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7352. Min Act: -0.1700
Data Index: 1425429 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7192. Min Act: -0.1700
Data Index: 1515966 (Python Code)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7192. Min Act: -0.1700
Data Index: 1384507 (Python Code)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7352. Min Act: -0.1700
Data Index: 1209008 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7352. Min Act: -0.1700
Data Index: 565029 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7512. Min Act: -0.1700
Data Index: 1297108 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7192. Min Act: -0.1700
Data Index: 401347 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8944. Min Range: -2.8944
Max Act: 2.7192. Min Act: -0.1700
Data Index: 1538136 (Python Code)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19