Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1090 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.3258. Min Act: -0.0001
Data Index: 702648 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2749. Min Act: -0.0001
Data Index: 1599763 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2783. Min Act: -0.0001
Data Index: 217644 (The Pile)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2559. Min Act: -0.0001
Data Index: 4715 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2577. Min Act: -0.0001
Data Index: 1494161 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2566. Min Act: -0.0001
Data Index: 1150378 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2545. Min Act: -0.0001
Data Index: 871236 (The Pile)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2451. Min Act: -0.0001
Data Index: 1382232 (The Pile)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2579. Min Act: -0.0001
Data Index: 887287 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2384. Min Act: -0.0001
Data Index: 10387 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2374. Min Act: -0.0001
Data Index: 69260 (The Pile)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2243. Min Act: -0.0001
Data Index: 1129757 (The Pile)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2218. Min Act: -0.0001
Data Index: 1014042 (The Pile)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2206. Min Act: -0.0001
Data Index: 1951200 (The Pile)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2209. Min Act: -0.0001
Data Index: 1498281 (The Pile)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2206. Min Act: -0.0001
Data Index: 738883 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2192. Min Act: -0.0001
Data Index: 225744 (The Pile)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2197. Min Act: -0.0001
Data Index: 1984706 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2329. Min Act: -0.0001
Data Index: 1032742 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3258. Min Range: -0.3258
Max Act: 0.2231. Min Act: -0.0001
Data Index: 811242 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19