Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 384 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.0093. Min Range: -5.0093
Max Act: 5.0093. Min Act: -0.1700
Data Index: 1267831 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.9155. Min Act: -0.1700
Data Index: 857064 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.8843. Min Act: -0.1700
Data Index: 1040182 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.9468. Min Act: -0.1700
Data Index: 524867 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.8843. Min Act: -0.1700
Data Index: 1305496 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.8530. Min Act: -0.1700
Data Index: 563320 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7593. Min Act: -0.1700
Data Index: 658060 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7593. Min Act: -0.1700
Data Index: 1299243 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7905. Min Act: -0.1700
Data Index: 843342 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7593. Min Act: -0.1700
Data Index: 897635 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.6343. Min Act: -0.1700
Data Index: 1022409 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.6030. Min Act: -0.1699
Data Index: 767321 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.6030. Min Act: -0.1700
Data Index: 799141 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.6343. Min Act: -0.1699
Data Index: 1327828 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.5718. Min Act: -0.1700
Data Index: 299618 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.5718. Min Act: -0.1700
Data Index: 583602 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.5405. Min Act: -0.1700
Data Index: 1101321 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.5093. Min Act: -0.1700
Data Index: 480773 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.5405. Min Act: -0.1700
Data Index: 291233 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.5405. Min Act: -0.1700
Data Index: 971513 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19