Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3983 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.3731. Min Act: -0.0001
Data Index: 527521 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.1144. Min Act: -0.0001
Data Index: 487748 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.2604. Min Act: -0.0001
Data Index: 703589 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.1545. Min Act: -0.0001
Data Index: 1118692 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.1291. Min Act: -0.0001
Data Index: 305755 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.2243. Min Act: -0.0001
Data Index: 623595 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.1453. Min Act: -0.0001
Data Index: 792160 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.2755. Min Act: -0.0001
Data Index: 894138 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.0589. Min Act: -0.0001
Data Index: 336678 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.1131. Min Act: -0.0001
Data Index: 973744 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.1601. Min Act: -0.0001
Data Index: 653716 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3731. Min Range: -1.3731
Max Act: 0.9969. Min Act: -0.0001
Data Index: 768802 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.0772. Min Act: -0.0001
Data Index: 1238083 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.0970. Min Act: -0.0001
Data Index: 516790 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3731. Min Range: -1.3731
Max Act: 0.9950. Min Act: -0.0001
Data Index: 404644 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.0204. Min Act: -0.0001
Data Index: 51247 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.0167. Min Act: -0.0001
Data Index: 600777 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3731. Min Range: -1.3731
Max Act: 0.8991. Min Act: -0.0001
Data Index: 366133 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3731. Min Range: -1.3731
Max Act: 1.0564. Min Act: -0.0001
Data Index: 350606 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3731. Min Range: -1.3731
Max Act: 0.7911. Min Act: -0.0001
Data Index: 1105596 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19