Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2007 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7816. Min Act: -0.1700
Data Index: 48745 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7816. Min Act: -0.1700
Data Index: 854099 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7497. Min Act: -0.1700
Data Index: 930299 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7337. Min Act: -0.1700
Data Index: 420941 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7337. Min Act: -0.1700
Data Index: 701263 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7337. Min Act: -0.1700
Data Index: 799385 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7337. Min Act: -0.1700
Data Index: 609468 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7177. Min Act: -0.1700
Data Index: 423091 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.6857. Min Act: -0.1700
Data Index: 216027 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7177. Min Act: -0.1700
Data Index: 42412 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7017. Min Act: -0.1700
Data Index: 298279 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.6857. Min Act: -0.1700
Data Index: 1130882 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7017. Min Act: -0.1700
Data Index: 530471 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7017. Min Act: -0.1700
Data Index: 282679 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7017. Min Act: -0.1700
Data Index: 547581 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.6857. Min Act: -0.1700
Data Index: 550374 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7177. Min Act: -0.1700
Data Index: 1328965 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7177. Min Act: -0.1700
Data Index: 80152 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.7177. Min Act: -0.1700
Data Index: 1020989 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7816. Min Range: -2.7816
Max Act: 2.6857. Min Act: -0.1700
Data Index: 249768 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19