Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 938 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.3285. Min Act: -0.0001
Data Index: 1458217 (The Pile)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.3365. Min Act: -0.0001
Data Index: 1779163 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2941. Min Act: -0.0001
Data Index: 1151839 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2835. Min Act: -0.0001
Data Index: 972141 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2854. Min Act: -0.0001
Data Index: 1488969 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2826. Min Act: -0.0001
Data Index: 1689381 (The Pile)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2906. Min Act: -0.0001
Data Index: 142136 (The Pile)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2595. Min Act: -0.0001
Data Index: 1344436 (The Pile)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2691. Min Act: -0.0001
Data Index: 280739 (The Pile)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2741. Min Act: -0.0001
Data Index: 1464209 (The Pile)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2222. Min Act: -0.0001
Data Index: 1118822 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2445. Min Act: -0.0001
Data Index: 151141 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2386. Min Act: -0.0001
Data Index: 1663077 (The Pile)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2347. Min Act: -0.0001
Data Index: 649658 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2385. Min Act: -0.0001
Data Index: 393697 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2450. Min Act: -0.0001
Data Index: 744937 (The Pile)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2150. Min Act: -0.0001
Data Index: 1466448 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2408. Min Act: -0.0001
Data Index: 1487036 (The Pile)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2572. Min Act: -0.0001
Data Index: 451288 (The Pile)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3365. Min Range: -0.3365
Max Act: 0.2460. Min Act: -0.0001
Data Index: 1414502 (The Pile)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19