Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1256 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3474. Min Range: -4.3474
Max Act: 4.3474. Min Act: -0.1700
Data Index: 1524193 (Python Code)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3474. Min Range: -4.3474
Max Act: 4.2693. Min Act: -0.1700
Data Index: 1257540 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3474. Min Range: -4.3474
Max Act: 4.2536. Min Act: -0.1700
Data Index: 1141213 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3474. Min Range: -4.3474
Max Act: 4.2536. Min Act: -0.1700
Data Index: 1050925 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3474. Min Range: -4.3474
Max Act: 4.1599. Min Act: -0.1700
Data Index: 977292 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3474. Min Range: -4.3474
Max Act: 4.1286. Min Act: -0.1700
Data Index: 631380 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3474. Min Range: -4.3474
Max Act: 4.0817. Min Act: -0.1700
Data Index: 293596 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3474. Min Range: -4.3474
Max Act: 4.0817. Min Act: -0.1700
Data Index: 659135 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3474. Min Range: -4.3474
Max Act: 4.0504. Min Act: -0.1699
Data Index: 76612 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3474. Min Range: -4.3474
Max Act: 4.0504. Min Act: -0.1700
Data Index: 1529273 (Python Code)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3474. Min Range: -4.3474
Max Act: 4.0036. Min Act: -0.1700
Data Index: 1000743 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3474. Min Range: -4.3474
Max Act: 4.0504. Min Act: -0.1700
Data Index: 1548118 (Python Code)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3474. Min Range: -4.3474
Max Act: 4.0504. Min Act: -0.1700
Data Index: 36604 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3474. Min Range: -4.3474
Max Act: 3.9410. Min Act: -0.1700
Data Index: 421847 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3474. Min Range: -4.3474
Max Act: 3.9254. Min Act: -0.1700
Data Index: 125903 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3474. Min Range: -4.3474
Max Act: 3.9410. Min Act: -0.1700
Data Index: 1115657 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3474. Min Range: -4.3474
Max Act: 3.9567. Min Act: -0.1700
Data Index: 1529355 (Python Code)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3474. Min Range: -4.3474
Max Act: 3.9410. Min Act: -0.1700
Data Index: 495764 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3474. Min Range: -4.3474
Max Act: 3.9410. Min Act: -0.1700
Data Index: 867342 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3474. Min Range: -4.3474
Max Act: 3.9410. Min Act: -0.1700
Data Index: 1131412 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19