Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2000 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.8920. Min Act: -0.1700
Data Index: 391540 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.8444. Min Act: -0.1700
Data Index: 84870 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.8285. Min Act: -0.1700
Data Index: 470600 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.8444. Min Act: -0.1700
Data Index: 138330 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.8126. Min Act: -0.1700
Data Index: 1641442 (Python Code)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7966. Min Act: -0.1700
Data Index: 1180196 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7966. Min Act: -0.1700
Data Index: 696553 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7966. Min Act: -0.1700
Data Index: 1337585 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7807. Min Act: -0.1700
Data Index: 989345 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7966. Min Act: -0.1700
Data Index: 1192633 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7648. Min Act: -0.1700
Data Index: 1145512 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7648. Min Act: -0.1700
Data Index: 1108618 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7488. Min Act: -0.1700
Data Index: 352067 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7648. Min Act: -0.1700
Data Index: 362489 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7488. Min Act: -0.1700
Data Index: 900104 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7488. Min Act: -0.1700
Data Index: 864270 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7488. Min Act: -0.1700
Data Index: 389918 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7648. Min Act: -0.1700
Data Index: 1072118 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7488. Min Act: -0.1700
Data Index: 633265 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8920. Min Range: -2.8920
Max Act: 2.7648. Min Act: -0.1700
Data Index: 1062950 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19