Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1989 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.5916. Min Act: -0.1700
Data Index: 1313493 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.4979. Min Act: -0.1700
Data Index: 761037 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.4979. Min Act: -0.1700
Data Index: 1115682 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.4510. Min Act: -0.1700
Data Index: 285197 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.4198. Min Act: -0.1700
Data Index: 1049750 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.3573. Min Act: -0.1700
Data Index: 1288918 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.3260. Min Act: -0.1700
Data Index: 95584 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.3729. Min Act: -0.1700
Data Index: 476853 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.4041. Min Act: -0.1700
Data Index: 180631 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.3416. Min Act: -0.1700
Data Index: 402898 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.3260. Min Act: -0.1700
Data Index: 317507 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.3416. Min Act: -0.1700
Data Index: 525708 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.3260. Min Act: -0.1700
Data Index: 1146041 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.3416. Min Act: -0.1700
Data Index: 1183327 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.2791. Min Act: -0.1700
Data Index: 262057 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.2947. Min Act: -0.1700
Data Index: 463543 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.2322. Min Act: -0.1700
Data Index: 887998 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.2947. Min Act: -0.1700
Data Index: 567165 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.2791. Min Act: -0.1700
Data Index: 902069 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5916. Min Range: -4.5916
Max Act: 4.2479. Min Act: -0.1700
Data Index: 43087 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19