Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1086 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.6536. Min Act: -0.1700
Data Index: 1101417 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.6376. Min Act: -0.1700
Data Index: 593000 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.6215. Min Act: -0.1700
Data Index: 51589 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.6054. Min Act: -0.1700
Data Index: 383169 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.6054. Min Act: -0.1700
Data Index: 524325 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.5893. Min Act: -0.1700
Data Index: 593461 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.5571. Min Act: -0.1700
Data Index: 646513 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.5410. Min Act: -0.1700
Data Index: 665771 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.5410. Min Act: -0.1700
Data Index: 202464 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.5248. Min Act: -0.1699
Data Index: 455252 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.5248. Min Act: -0.1700
Data Index: 1332391 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.5248. Min Act: -0.1700
Data Index: 644403 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.5086. Min Act: -0.1700
Data Index: 77296 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.4924. Min Act: -0.1700
Data Index: 32402 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.4924. Min Act: -0.1700
Data Index: 348134 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.5086. Min Act: -0.1700
Data Index: 575241 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.5086. Min Act: -0.1700
Data Index: 486431 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.4924. Min Act: -0.1700
Data Index: 206400 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.4924. Min Act: -0.1700
Data Index: 397816 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6536. Min Range: -2.6536
Max Act: 2.4924. Min Act: -0.1700
Data Index: 1137429 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19