Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1304 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.2139. Min Range: -3.2139
Max Act: 3.2139. Min Act: -0.1700
Data Index: 1110579 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2139. Min Range: -3.2139
Max Act: 3.0564. Min Act: -0.1700
Data Index: 708156 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2139. Min Range: -3.2139
Max Act: 3.0406. Min Act: -0.1700
Data Index: 321986 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2139. Min Range: -3.2139
Max Act: 3.0406. Min Act: -0.1700
Data Index: 1104651 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2139. Min Range: -3.2139
Max Act: 3.0248. Min Act: -0.1700
Data Index: 954873 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2139. Min Range: -3.2139
Max Act: 3.0090. Min Act: -0.1700
Data Index: 1223986 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9774. Min Act: -0.1700
Data Index: 1340162 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9932. Min Act: -0.1700
Data Index: 962561 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9774. Min Act: -0.1700
Data Index: 363789 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9774. Min Act: -0.1700
Data Index: 198252 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9932. Min Act: -0.1700
Data Index: 204424 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9774. Min Act: -0.1700
Data Index: 258830 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9616. Min Act: -0.1700
Data Index: 825581 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9616. Min Act: -0.1700
Data Index: 855169 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9299. Min Act: -0.1700
Data Index: 483292 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9140. Min Act: -0.1700
Data Index: 709027 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9457. Min Act: -0.1700
Data Index: 368843 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9457. Min Act: -0.1700
Data Index: 898600 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9299. Min Act: -0.1700
Data Index: 729444 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2139. Min Range: -3.2139
Max Act: 2.9299. Min Act: -0.1700
Data Index: 197512 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19