Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2744 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0432. Min Act: -0.0001
Data Index: 920405 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0408. Min Act: -0.0000
Data Index: 1487854 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0398. Min Act: -0.0001
Data Index: 258802 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0383. Min Act: -0.0001
Data Index: 739202 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0382. Min Act: -0.0001
Data Index: 1045998 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0371. Min Act: -0.0001
Data Index: 1101737 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0369. Min Act: -0.0001
Data Index: 194120 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0369. Min Act: -0.0001
Data Index: 1370446 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0356. Min Act: -0.0001
Data Index: 1167129 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0366. Min Act: -0.0001
Data Index: 712145 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0365. Min Act: -0.0001
Data Index: 1517715 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0366. Min Act: -0.0001
Data Index: 629691 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0365. Min Act: -0.0001
Data Index: 1351196 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0365. Min Act: -0.0001
Data Index: 483822 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0365. Min Act: -0.0001
Data Index: 1219073 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0365. Min Act: -0.0001
Data Index: 778298 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0365. Min Act: -0.0001
Data Index: 1914168 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0365. Min Act: -0.0001
Data Index: 1135524 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0365. Min Act: -0.0001
Data Index: 225561 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0432. Min Range: -0.0432
Max Act: 0.0364. Min Act: -0.0001
Data Index: 1610667 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19