Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 267 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.5955. Min Act: -0.1700
Data Index: 143280 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.5955. Min Act: -0.1700
Data Index: 671078 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.5330. Min Act: -0.1700
Data Index: 1285564 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.4705. Min Act: -0.1700
Data Index: 1266077 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.3455. Min Act: -0.1700
Data Index: 1493446 (Python Code)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.3455. Min Act: -0.1700
Data Index: 757678 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.3143. Min Act: -0.1700
Data Index: 1126598 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.3143. Min Act: -0.1700
Data Index: 426248 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.2830. Min Act: -0.1700
Data Index: 489564 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.2517. Min Act: -0.1700
Data Index: 1340303 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.2830. Min Act: -0.1700
Data Index: 1472429 (Python Code)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.3455. Min Act: -0.1700
Data Index: 1525400 (Python Code)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.3143. Min Act: -0.1700
Data Index: 348954 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.1892. Min Act: -0.1700
Data Index: 980825 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.2830. Min Act: -0.1700
Data Index: 970635 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.3455. Min Act: -0.1700
Data Index: 897276 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.3768. Min Act: -0.1700
Data Index: 1259884 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.3143. Min Act: -0.1700
Data Index: 692415 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.2205. Min Act: -0.1700
Data Index: 1655183 (Python Code)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5955. Min Range: -4.5955
Max Act: 4.2830. Min Act: -0.1700
Data Index: 1473122 (Python Code)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19