Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 4225 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.9290. Min Act: -0.0000
Data Index: 328847 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.5900. Min Act: -0.0000
Data Index: 121275 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.5374. Min Act: -0.0000
Data Index: 1485384 (The Pile)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.4027. Min Act: -0.0000
Data Index: 59585 (The Pile)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.3676. Min Act: -0.0000
Data Index: 89571 (The Pile)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.3836. Min Act: -0.0000
Data Index: 1541126 (The Pile)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.3095. Min Act: -0.0000
Data Index: 1669608 (The Pile)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.2462. Min Act: -0.0000
Data Index: 633758 (The Pile)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.2781. Min Act: -0.0000
Data Index: 898289 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.2880. Min Act: -0.0000
Data Index: 37203 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.3191. Min Act: -0.0000
Data Index: 1079865 (The Pile)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.4209. Min Act: -0.0000
Data Index: 1536317 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.2517. Min Act: -0.0000
Data Index: 1932227 (The Pile)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.1728. Min Act: -0.0000
Data Index: 873414 (The Pile)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.2978. Min Act: -0.0000
Data Index: 1165307 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.2448. Min Act: -0.0000
Data Index: 1380768 (The Pile)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.0821. Min Act: -0.0000
Data Index: 1913000 (The Pile)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.2329. Min Act: -0.0000
Data Index: 373086 (The Pile)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.2186. Min Act: -0.0000
Data Index: 1720478 (The Pile)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9290. Min Range: -1.9290
Max Act: 1.1801. Min Act: -0.0000
Data Index: 1339562 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19