Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.1206. Min Range: -3.1206
Max Act: 3.1206. Min Act: -0.1700
Data Index: 1153894 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1206. Min Range: -3.1206
Max Act: 3.0575. Min Act: -0.1700
Data Index: 803519 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1206. Min Range: -3.1206
Max Act: 3.0575. Min Act: -0.1700
Data Index: 1455708 (Python Code)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1206. Min Range: -3.1206
Max Act: 3.0259. Min Act: -0.1700
Data Index: 310624 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.9785. Min Act: -0.1700
Data Index: 991499 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.9627. Min Act: -0.1700
Data Index: 507620 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.9468. Min Act: -0.1700
Data Index: 1019013 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.9310. Min Act: -0.1700
Data Index: 947205 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.9310. Min Act: -0.1700
Data Index: 817758 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.8993. Min Act: -0.1700
Data Index: 1306435 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.8834. Min Act: -0.1700
Data Index: 179092 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.8993. Min Act: -0.1700
Data Index: 358659 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.8675. Min Act: -0.1700
Data Index: 44227 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.8358. Min Act: -0.1700
Data Index: 237237 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.8675. Min Act: -0.1700
Data Index: 473002 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.8675. Min Act: -0.1700
Data Index: 1514500 (Python Code)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.8358. Min Act: -0.1700
Data Index: 606777 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.8517. Min Act: -0.1700
Data Index: 310702 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.8358. Min Act: -0.1700
Data Index: 101390 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1206. Min Range: -3.1206
Max Act: 2.8358. Min Act: -0.1700
Data Index: 562713 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19