Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1985 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.6869. Min Act: -0.1700
Data Index: 203526 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.6709. Min Act: -0.1699
Data Index: 138536 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.6067. Min Act: -0.1700
Data Index: 22438 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.5099. Min Act: -0.1700
Data Index: 75668 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.4775. Min Act: -0.1700
Data Index: 984685 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.4613. Min Act: -0.1700
Data Index: 494451 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.4450. Min Act: -0.1700
Data Index: 628518 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.4450. Min Act: -0.1700
Data Index: 915947 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.4287. Min Act: -0.1700
Data Index: 496510 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.4450. Min Act: -0.1700
Data Index: 1195843 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.3961. Min Act: -0.1700
Data Index: 1081331 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.3961. Min Act: -0.1700
Data Index: 986238 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.4125. Min Act: -0.1700
Data Index: 305136 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.3961. Min Act: -0.1700
Data Index: 887402 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.3798. Min Act: -0.1700
Data Index: 132101 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.3798. Min Act: -0.1700
Data Index: 30432 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.3635. Min Act: -0.1700
Data Index: 1279061 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.3471. Min Act: -0.1700
Data Index: 240062 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.3471. Min Act: -0.1700
Data Index: 1249086 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6869. Min Range: -2.6869
Max Act: 2.3471. Min Act: -0.1700
Data Index: 615314 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19