Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 66 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.6470. Min Range: -4.6470
Max Act: 4.6007. Min Act: -0.0001
Data Index: 891089 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6470. Min Range: -4.6470
Max Act: 4.6470. Min Act: -0.0001
Data Index: 1151186 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6470. Min Range: -4.6470
Max Act: 4.2758. Min Act: -0.0001
Data Index: 251510 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6470. Min Range: -4.6470
Max Act: 4.2947. Min Act: -0.0001
Data Index: 1067102 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6470. Min Range: -4.6470
Max Act: 4.2227. Min Act: -0.0001
Data Index: 202466 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6470. Min Range: -4.6470
Max Act: 4.1685. Min Act: -0.0001
Data Index: 608262 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6470. Min Range: -4.6470
Max Act: 4.2344. Min Act: -0.0001
Data Index: 958960 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6470. Min Range: -4.6470
Max Act: 3.7183. Min Act: -0.0001
Data Index: 210481 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6470. Min Range: -4.6470
Max Act: 4.0126. Min Act: -0.0001
Data Index: 352189 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6470. Min Range: -4.6470
Max Act: 3.4466. Min Act: -0.0001
Data Index: 593297 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6470. Min Range: -4.6470
Max Act: 3.3076. Min Act: -0.0001
Data Index: 935078 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6470. Min Range: -4.6470
Max Act: 3.6111. Min Act: -0.0001
Data Index: 486953 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6470. Min Range: -4.6470
Max Act: 3.7553. Min Act: -0.0001
Data Index: 144384 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6470. Min Range: -4.6470
Max Act: 3.4158. Min Act: -0.0001
Data Index: 799457 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6470. Min Range: -4.6470
Max Act: 3.6728. Min Act: -0.0001
Data Index: 958449 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6470. Min Range: -4.6470
Max Act: 3.3517. Min Act: -0.0001
Data Index: 1123988 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6470. Min Range: -4.6470
Max Act: 3.3055. Min Act: -0.0001
Data Index: 901197 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6470. Min Range: -4.6470
Max Act: 3.2764. Min Act: -0.0001
Data Index: 537261 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6470. Min Range: -4.6470
Max Act: 3.4288. Min Act: -0.0001
Data Index: 311534 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6470. Min Range: -4.6470
Max Act: 3.5927. Min Act: -0.0001
Data Index: 105154 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19