Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3091 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 4.7700. Min Range: -4.7700
Max Act: 4.7700. Min Act: 0.0001
Data Index: 1136482 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7700. Min Range: -4.7700
Max Act: 4.7566. Min Act: 0.0000
Data Index: 181257 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7700. Min Range: -4.7700
Max Act: 4.1020. Min Act: 0.0000
Data Index: 1860688 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7700. Min Range: -4.7700
Max Act: 4.0602. Min Act: -0.0000
Data Index: 257007 (The Pile)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7700. Min Range: -4.7700
Max Act: 4.0306. Min Act: 0.0000
Data Index: 786098 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7700. Min Range: -4.7700
Max Act: 4.0872. Min Act: 0.0001
Data Index: 1235869 (The Pile)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7700. Min Range: -4.7700
Max Act: 4.2171. Min Act: 0.0000
Data Index: 1111974 (The Pile)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7700. Min Range: -4.7700
Max Act: 4.2106. Min Act: 0.0001
Data Index: 1618917 (The Pile)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7700. Min Range: -4.7700
Max Act: 3.9525. Min Act: -0.0000
Data Index: 429377 (The Pile)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7700. Min Range: -4.7700
Max Act: 3.9472. Min Act: -0.0000
Data Index: 1135498 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7700. Min Range: -4.7700
Max Act: 3.7781. Min Act: 0.0000
Data Index: 97016 (The Pile)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7700. Min Range: -4.7700
Max Act: 3.9215. Min Act: 0.0000
Data Index: 379382 (The Pile)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7700. Min Range: -4.7700
Max Act: 3.7167. Min Act: 0.0000
Data Index: 1930097 (The Pile)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7700. Min Range: -4.7700
Max Act: 3.9018. Min Act: -0.0000
Data Index: 1094862 (The Pile)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7700. Min Range: -4.7700
Max Act: 3.9403. Min Act: -0.0000
Data Index: 254897 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7700. Min Range: -4.7700
Max Act: 3.5989. Min Act: -0.0000
Data Index: 63666 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7700. Min Range: -4.7700
Max Act: 3.7612. Min Act: -0.0000
Data Index: 636837 (The Pile)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7700. Min Range: -4.7700
Max Act: 3.7155. Min Act: 0.0001
Data Index: 1358601 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7700. Min Range: -4.7700
Max Act: 3.5642. Min Act: 0.0000
Data Index: 720307 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7700. Min Range: -4.7700
Max Act: 3.8735. Min Act: 0.0000
Data Index: 1610383 (The Pile)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19