Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 57 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.8761. Min Act: -0.1700
Data Index: 531487 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.6261. Min Act: -0.1700
Data Index: 477211 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.5636. Min Act: -0.1692
Data Index: 639546 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.5636. Min Act: -0.1700
Data Index: 1319964 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.5636. Min Act: -0.1700
Data Index: 1107392 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.5011. Min Act: -0.1700
Data Index: 324348 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.5011. Min Act: -0.1699
Data Index: 526686 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.5011. Min Act: -0.1699
Data Index: 376204 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.4386. Min Act: -0.1699
Data Index: 528941 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.3136. Min Act: -0.1700
Data Index: 145607 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.3136. Min Act: -0.1699
Data Index: 914031 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.3136. Min Act: -0.1699
Data Index: 245061 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.2511. Min Act: -0.1699
Data Index: 952928 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.3136. Min Act: -0.1700
Data Index: 454258 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.2511. Min Act: -0.1700
Data Index: 1600028 (Python Code)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.2511. Min Act: -0.1700
Data Index: 1199455 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.2511. Min Act: -0.1700
Data Index: 1275749 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.1886. Min Act: -0.1700
Data Index: 234164 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.1886. Min Act: -0.1700
Data Index: 509395 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8761. Min Range: -6.8761
Max Act: 6.1261. Min Act: -0.1699
Data Index: 587429 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19