Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2012 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.4945. Min Range: -1.4945
Max Act: 1.4945. Min Act: -0.0000
Data Index: 1111604 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4945. Min Range: -1.4945
Max Act: 1.1918. Min Act: -0.0000
Data Index: 204039 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4945. Min Range: -1.4945
Max Act: 1.1976. Min Act: -0.0000
Data Index: 1979819 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4945. Min Range: -1.4945
Max Act: 1.0609. Min Act: -0.0000
Data Index: 47989 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4945. Min Range: -1.4945
Max Act: 1.0178. Min Act: -0.0000
Data Index: 1305495 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4945. Min Range: -1.4945
Max Act: 1.0622. Min Act: -0.0000
Data Index: 1895469 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4945. Min Range: -1.4945
Max Act: 1.0815. Min Act: -0.0000
Data Index: 264654 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4945. Min Range: -1.4945
Max Act: 0.9536. Min Act: -0.0000
Data Index: 1501974 (The Pile)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4945. Min Range: -1.4945
Max Act: 0.9665. Min Act: -0.0000
Data Index: 1687630 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4945. Min Range: -1.4945
Max Act: 0.9169. Min Act: -0.0000
Data Index: 1258300 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4945. Min Range: -1.4945
Max Act: 0.9350. Min Act: -0.0000
Data Index: 21290 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4945. Min Range: -1.4945
Max Act: 0.9233. Min Act: -0.0000
Data Index: 276966 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4945. Min Range: -1.4945
Max Act: 0.9370. Min Act: -0.0000
Data Index: 779276 (The Pile)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4945. Min Range: -1.4945
Max Act: 1.0150. Min Act: -0.0000
Data Index: 1397793 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4945. Min Range: -1.4945
Max Act: 0.8999. Min Act: -0.0000
Data Index: 1745334 (The Pile)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4945. Min Range: -1.4945
Max Act: 0.8912. Min Act: -0.0000
Data Index: 1329027 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4945. Min Range: -1.4945
Max Act: 0.9330. Min Act: 0.0000
Data Index: 1263965 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4945. Min Range: -1.4945
Max Act: 0.9024. Min Act: -0.0000
Data Index: 1281607 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4945. Min Range: -1.4945
Max Act: 0.9496. Min Act: -0.0000
Data Index: 1379229 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4945. Min Range: -1.4945
Max Act: 0.9081. Min Act: -0.0000
Data Index: 1233983 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19