Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1979 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.7706. Min Act: -0.1700
Data Index: 446443 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.7547. Min Act: -0.1700
Data Index: 701914 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.7387. Min Act: -0.1700
Data Index: 805605 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.7547. Min Act: -0.1700
Data Index: 81359 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.6907. Min Act: -0.1700
Data Index: 657912 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.6907. Min Act: -0.1700
Data Index: 726708 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.6747. Min Act: -0.1700
Data Index: 1190151 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.6907. Min Act: -0.1700
Data Index: 1284045 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.6587. Min Act: -0.1700
Data Index: 89720 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.6427. Min Act: -0.1700
Data Index: 1031329 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.6427. Min Act: -0.1700
Data Index: 1319467 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.6105. Min Act: -0.1700
Data Index: 264057 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.5944. Min Act: -0.1700
Data Index: 1232271 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.5944. Min Act: -0.1700
Data Index: 1164589 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.5944. Min Act: -0.1700
Data Index: 609255 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.5944. Min Act: -0.1700
Data Index: 1313917 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.5944. Min Act: -0.1700
Data Index: 897442 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.5944. Min Act: -0.1700
Data Index: 490140 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.5944. Min Act: -0.1700
Data Index: 895194 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7706. Min Range: -2.7706
Max Act: 2.5783. Min Act: -0.1700
Data Index: 1053 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19