Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 112 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.5158. Min Act: -0.1700
Data Index: 376348 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.4846. Min Act: -0.1700
Data Index: 405400 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.4533. Min Act: -0.1700
Data Index: 524738 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.3596. Min Act: -0.1700
Data Index: 1297934 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.4221. Min Act: -0.1700
Data Index: 988642 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.3908. Min Act: -0.1700
Data Index: 1321677 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.3596. Min Act: -0.1700
Data Index: 1298519 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.3596. Min Act: -0.1700
Data Index: 1264505 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.3596. Min Act: -0.1700
Data Index: 691368 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.3283. Min Act: -0.1700
Data Index: 719522 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.2971. Min Act: -0.1700
Data Index: 736398 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.2971. Min Act: -0.1700
Data Index: 42290 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.2658. Min Act: -0.1700
Data Index: 211025 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.3283. Min Act: -0.1700
Data Index: 313056 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.2971. Min Act: -0.1700
Data Index: 824332 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.2658. Min Act: -0.1700
Data Index: 187101 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.2971. Min Act: -0.1700
Data Index: 160072 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.2658. Min Act: -0.1700
Data Index: 307800 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.2658. Min Act: -0.1700
Data Index: 368846 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5158. Min Range: -4.5158
Max Act: 4.2971. Min Act: -0.1700
Data Index: 1042169 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19