Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 283 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.4869. Min Act: -0.1700
Data Index: 871200 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.4244. Min Act: -0.1700
Data Index: 717915 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.4244. Min Act: -0.1700
Data Index: 840954 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.3619. Min Act: -0.1700
Data Index: 1286977 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2994. Min Act: -0.1700
Data Index: 863498 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2681. Min Act: -0.1700
Data Index: 1065673 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2994. Min Act: -0.1700
Data Index: 675811 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2994. Min Act: -0.1700
Data Index: 206020 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2994. Min Act: -0.1700
Data Index: 215447 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2994. Min Act: -0.1700
Data Index: 1339613 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.3306. Min Act: -0.1700
Data Index: 206067 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2681. Min Act: -0.1700
Data Index: 437238 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2056. Min Act: -0.1700
Data Index: 122696 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2369. Min Act: -0.1700
Data Index: 835208 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2056. Min Act: -0.1700
Data Index: 756897 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2056. Min Act: -0.1700
Data Index: 441353 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2369. Min Act: -0.1700
Data Index: 571283 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2681. Min Act: -0.1700
Data Index: 902555 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.2369. Min Act: -0.1700
Data Index: 666504 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4869. Min Range: -6.4869
Max Act: 6.1119. Min Act: -0.1700
Data Index: 219648 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19