Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1644 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.5982. Min Act: -0.0001
Data Index: 1351158 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.5026. Min Act: -0.0001
Data Index: 215488 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4982. Min Act: -0.0001
Data Index: 341551 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4734. Min Act: -0.0001
Data Index: 454912 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4799. Min Act: -0.0001
Data Index: 1066108 (The Pile)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.3993. Min Act: -0.0001
Data Index: 1343512 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.5081. Min Act: -0.0001
Data Index: 1323192 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4765. Min Act: -0.0001
Data Index: 554153 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4666. Min Act: -0.0001
Data Index: 1631234 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4098. Min Act: -0.0001
Data Index: 1450036 (The Pile)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4208. Min Act: -0.0001
Data Index: 1744017 (The Pile)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4328. Min Act: -0.0001
Data Index: 1587693 (The Pile)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4269. Min Act: -0.0001
Data Index: 825224 (The Pile)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4071. Min Act: -0.0001
Data Index: 1906042 (The Pile)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4699. Min Act: -0.0001
Data Index: 1370547 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4129. Min Act: -0.0001
Data Index: 822233 (The Pile)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4496. Min Act: -0.0001
Data Index: 775992 (The Pile)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.3896. Min Act: -0.0001
Data Index: 1228430 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4072. Min Act: -0.0001
Data Index: 787234 (The Pile)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5982. Min Range: -0.5982
Max Act: 0.4271. Min Act: -0.0001
Data Index: 488539 (The Pile)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19