Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 231 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.8749. Min Act: -0.1700
Data Index: 841184 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.7187. Min Act: -0.1700
Data Index: 482568 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.7499. Min Act: -0.1700
Data Index: 479015 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.6562. Min Act: -0.1700
Data Index: 821503 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.6249. Min Act: -0.1700
Data Index: 46825 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.5624. Min Act: -0.1700
Data Index: 636178 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.5312. Min Act: -0.1700
Data Index: 883641 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.6249. Min Act: -0.1700
Data Index: 20154 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.5937. Min Act: -0.1700
Data Index: 123190 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.5624. Min Act: -0.1700
Data Index: 64925 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.5624. Min Act: -0.1700
Data Index: 901591 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.5624. Min Act: -0.1700
Data Index: 591086 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.5624. Min Act: -0.1700
Data Index: 1116351 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.4687. Min Act: -0.1700
Data Index: 718844 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.4999. Min Act: -0.1700
Data Index: 1247187 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.4687. Min Act: -0.1700
Data Index: 793626 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.4374. Min Act: -0.1700
Data Index: 64640 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.4687. Min Act: -0.1700
Data Index: 526550 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.4687. Min Act: -0.1700
Data Index: 883227 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8749. Min Range: -4.8749
Max Act: 4.4687. Min Act: -0.1700
Data Index: 335836 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19