Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2507 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.3131. Min Act: -0.0002
Data Index: 1899457 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.2887. Min Act: -0.0002
Data Index: 670186 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.1947. Min Act: -0.0002
Data Index: 1286095 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.1606. Min Act: -0.0002
Data Index: 1484193 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.1547. Min Act: -0.0002
Data Index: 607177 (The Pile)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.1312. Min Act: -0.0002
Data Index: 50394 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.1546. Min Act: -0.0002
Data Index: 1006099 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.1519. Min Act: -0.0002
Data Index: 1275642 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.1436. Min Act: -0.0002
Data Index: 731481 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.0821. Min Act: -0.0002
Data Index: 83868 (The Pile)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.0457. Min Act: -0.0002
Data Index: 1954632 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.0787. Min Act: -0.0002
Data Index: 1458353 (The Pile)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.0670. Min Act: -0.0002
Data Index: 1321134 (The Pile)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.0237. Min Act: -0.0002
Data Index: 1583746 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.0422. Min Act: -0.0002
Data Index: 568195 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.0729. Min Act: -0.0002
Data Index: 1092382 (The Pile)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.0105. Min Act: -0.0002
Data Index: 216276 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.0327. Min Act: -0.0002
Data Index: 1487758 (The Pile)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.0176. Min Act: -0.0002
Data Index: 702468 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3131. Min Range: -1.3131
Max Act: 1.0351. Min Act: -0.0002
Data Index: 1873351 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19