Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 108 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.0210. Min Range: -5.0210
Max Act: 5.0210. Min Act: -0.1700
Data Index: 138383 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.9585. Min Act: -0.1700
Data Index: 875129 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.9273. Min Act: -0.1700
Data Index: 442812 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.9585. Min Act: -0.1700
Data Index: 1312187 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.9273. Min Act: -0.1700
Data Index: 1219555 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.8648. Min Act: -0.1700
Data Index: 342008 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.8335. Min Act: -0.1700
Data Index: 344498 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.8960. Min Act: -0.1700
Data Index: 1171497 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.8648. Min Act: -0.1700
Data Index: 550394 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.8023. Min Act: -0.1700
Data Index: 287980 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.8335. Min Act: -0.1700
Data Index: 910659 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.8023. Min Act: -0.1700
Data Index: 1307563 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.8335. Min Act: -0.1700
Data Index: 724047 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.8335. Min Act: -0.1700
Data Index: 581218 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.7398. Min Act: -0.1700
Data Index: 565241 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.7398. Min Act: -0.1700
Data Index: 220099 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.7710. Min Act: -0.1700
Data Index: 937708 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.8023. Min Act: -0.1700
Data Index: 873263 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.8023. Min Act: -0.1700
Data Index: 444406 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0210. Min Range: -5.0210
Max Act: 4.7710. Min Act: -0.1700
Data Index: 599743 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19