Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 372 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.6207. Min Act: -0.1700
Data Index: 279720 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.5894. Min Act: -0.1700
Data Index: 105628 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.4331. Min Act: -0.1700
Data Index: 868948 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.4019. Min Act: -0.1700
Data Index: 741769 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.3706. Min Act: -0.1699
Data Index: 690952 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.3394. Min Act: -0.1700
Data Index: 1091092 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.3394. Min Act: -0.1700
Data Index: 118383 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.2769. Min Act: -0.1700
Data Index: 949774 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.2144. Min Act: -0.1700
Data Index: 819700 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.2769. Min Act: -0.1700
Data Index: 442613 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.2144. Min Act: -0.1700
Data Index: 768618 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.1831. Min Act: -0.1700
Data Index: 554647 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.1831. Min Act: -0.1699
Data Index: 306413 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.2144. Min Act: -0.1700
Data Index: 130921 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.1831. Min Act: -0.1700
Data Index: 884356 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.1831. Min Act: -0.1700
Data Index: 413631 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.1831. Min Act: -0.1700
Data Index: 1339741 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.1206. Min Act: -0.1699
Data Index: 393149 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.1518. Min Act: -0.1700
Data Index: 68258 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6207. Min Range: -4.6207
Max Act: 4.1518. Min Act: -0.1699
Data Index: 425504 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19