Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1790 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.3427. Min Act: -0.1700
Data Index: 371542 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.3427. Min Act: -0.1700
Data Index: 477690 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.3263. Min Act: -0.1700
Data Index: 1415342 (Python Code)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.3263. Min Act: -0.1700
Data Index: 1417876 (Python Code)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.3263. Min Act: -0.1700
Data Index: 1446215 (Python Code)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.3263. Min Act: -0.1700
Data Index: 1446654 (Python Code)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.3263. Min Act: -0.1700
Data Index: 1590901 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.2934. Min Act: -0.1700
Data Index: 1431105 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.2605. Min Act: -0.1700
Data Index: 861362 (C4 (Web Text))
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.2440. Min Act: -0.1700
Data Index: 929451 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.2605. Min Act: -0.1700
Data Index: 713245 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.2440. Min Act: -0.1700
Data Index: 792905 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.2440. Min Act: -0.1700
Data Index: 167063 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.2605. Min Act: -0.1700
Data Index: 885525 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.2605. Min Act: -0.1700
Data Index: 1126783 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.2440. Min Act: -0.1700
Data Index: 1096115 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.2440. Min Act: -0.1700
Data Index: 426513 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.2605. Min Act: -0.1700
Data Index: 966397 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.2440. Min Act: -0.1700
Data Index: 964805 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3427. Min Range: -2.3427
Max Act: 2.2275. Min Act: -0.1658
Data Index: 911499 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19