Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 15 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.4476. Min Act: -0.1700
Data Index: 159489 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.5101. Min Act: -0.1700
Data Index: 1262403 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.4789. Min Act: -0.1700
Data Index: 269743 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.4164. Min Act: -0.1700
Data Index: 486731 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.4164. Min Act: -0.1700
Data Index: 864354 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.3539. Min Act: -0.1700
Data Index: 584675 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.3226. Min Act: -0.1700
Data Index: 612871 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.2913. Min Act: -0.1700
Data Index: 358000 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.2288. Min Act: -0.1700
Data Index: 1043100 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.2601. Min Act: -0.1700
Data Index: 483722 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.2601. Min Act: -0.1700
Data Index: 34195 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.2288. Min Act: -0.1700
Data Index: 305605 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.2288. Min Act: -0.1700
Data Index: 1280708 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.1976. Min Act: -0.1700
Data Index: 646336 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.1038. Min Act: -0.1700
Data Index: 161291 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.2288. Min Act: -0.1700
Data Index: 1287147 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.1663. Min Act: -0.1700
Data Index: 434053 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.1351. Min Act: -0.1700
Data Index: 423811 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.1663. Min Act: -0.1700
Data Index: 1047391 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5101. Min Range: -4.5101
Max Act: 4.1351. Min Act: -0.1700
Data Index: 507690 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19