Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 1764 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.3499. Min Act: -0.0001
Data Index: 922368 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2945. Min Act: -0.0001
Data Index: 979048 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2749. Min Act: -0.0001
Data Index: 866762 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2732. Min Act: -0.0001
Data Index: 280613 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2447. Min Act: -0.0001
Data Index: 1311414 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2315. Min Act: -0.0001
Data Index: 1962601 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2509. Min Act: -0.0001
Data Index: 307184 (The Pile)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2329. Min Act: -0.0001
Data Index: 1470749 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2288. Min Act: -0.0001
Data Index: 1788756 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2369. Min Act: -0.0001
Data Index: 402620 (The Pile)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2280. Min Act: -0.0001
Data Index: 101385 (The Pile)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2264. Min Act: -0.0001
Data Index: 1504586 (The Pile)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2405. Min Act: -0.0001
Data Index: 949651 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2405. Min Act: -0.0001
Data Index: 821421 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2307. Min Act: -0.0001
Data Index: 1909009 (The Pile)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2372. Min Act: -0.0001
Data Index: 709216 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2217. Min Act: -0.0001
Data Index: 661660 (The Pile)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2278. Min Act: -0.0001
Data Index: 1101683 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2251. Min Act: -0.0001
Data Index: 1183073 (The Pile)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3499. Min Range: -0.3499
Max Act: 0.2180. Min Act: -0.0001
Data Index: 1379945 (The Pile)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19