Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2937 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.0599. Min Range: -3.0599
Max Act: 3.0599. Min Act: -0.0001
Data Index: 159259 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.6094. Min Act: -0.0001
Data Index: 202984 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.5935. Min Act: -0.0001
Data Index: 416911 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.7401. Min Act: -0.0001
Data Index: 1089343 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.4920. Min Act: -0.0001
Data Index: 1025179 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.5637. Min Act: -0.0001
Data Index: 386764 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.3129. Min Act: -0.0001
Data Index: 1314966 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.4394. Min Act: -0.0001
Data Index: 989760 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.5133. Min Act: -0.0001
Data Index: 1192088 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.5163. Min Act: -0.0001
Data Index: 506238 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.6180. Min Act: -0.0001
Data Index: 1009114 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.3346. Min Act: -0.0001
Data Index: 83945 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.4935. Min Act: -0.0001
Data Index: 1209168 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.3406. Min Act: -0.0001
Data Index: 443658 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.6208. Min Act: -0.0001
Data Index: 1104428 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.3242. Min Act: -0.0001
Data Index: 1352765 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.4374. Min Act: -0.0001
Data Index: 414523 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.3121. Min Act: -0.0001
Data Index: 40560 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.5287. Min Act: -0.0001
Data Index: 316517 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0599. Min Range: -3.0599
Max Act: 2.2588. Min Act: -0.0001
Data Index: 13771 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19