Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2429 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2538. Min Act: -0.0002
Data Index: 16402 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2584. Min Act: -0.0002
Data Index: 1550324 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2464. Min Act: -0.0002
Data Index: 926768 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2450. Min Act: -0.0002
Data Index: 73502 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 1506960 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 204186 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 1153419 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 18722 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 421470 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 453977 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 1362679 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 650543 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 1086177 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 1444597 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 118793 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 1189631 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 628090 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 764256 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 504053 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2584. Min Range: -0.2584
Max Act: 0.2295. Min Act: -0.0002
Data Index: 983814 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19