Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1355 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.3153. Min Act: -0.1700
Data Index: 1337271 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.3466. Min Act: -0.1700
Data Index: 1185044 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.2528. Min Act: -0.1700
Data Index: 1293176 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.3466. Min Act: -0.1700
Data Index: 824480 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.2841. Min Act: -0.1700
Data Index: 810574 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.1590. Min Act: -0.1700
Data Index: 700963 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.2215. Min Act: -0.1700
Data Index: 459139 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.2841. Min Act: -0.1700
Data Index: 1046297 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.2215. Min Act: -0.1700
Data Index: 691862 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.2528. Min Act: -0.1700
Data Index: 179898 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.1590. Min Act: -0.1700
Data Index: 570772 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.1903. Min Act: -0.1700
Data Index: 1239553 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.1903. Min Act: -0.1700
Data Index: 1200744 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.1278. Min Act: -0.1700
Data Index: 400954 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.1903. Min Act: -0.1700
Data Index: 56948 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.1278. Min Act: -0.1700
Data Index: 853939 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.1590. Min Act: -0.1700
Data Index: 659543 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.1590. Min Act: -0.1700
Data Index: 79764 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.1590. Min Act: -0.1700
Data Index: 320770 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3466. Min Range: -4.3466
Max Act: 4.0965. Min Act: -0.1700
Data Index: 437004 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19