Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 300 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.5010. Min Act: -0.1700
Data Index: 786741 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.4848. Min Act: -0.1700
Data Index: 292439 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.4686. Min Act: -0.1700
Data Index: 1165658 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.4686. Min Act: -0.1700
Data Index: 568069 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.4686. Min Act: -0.1700
Data Index: 66285 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.4523. Min Act: -0.1700
Data Index: 84948 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.4361. Min Act: -0.1700
Data Index: 453311 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.4361. Min Act: -0.1700
Data Index: 55665 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.4198. Min Act: -0.1700
Data Index: 1198326 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.4198. Min Act: -0.1700
Data Index: 973235 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.4198. Min Act: -0.1700
Data Index: 459172 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.4198. Min Act: -0.1700
Data Index: 1103600 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.3872. Min Act: -0.1700
Data Index: 222036 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.4035. Min Act: -0.1700
Data Index: 427142 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.3872. Min Act: -0.1700
Data Index: 1115819 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.3872. Min Act: -0.1700
Data Index: 46613 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.3872. Min Act: -0.1700
Data Index: 777763 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.3872. Min Act: -0.1700
Data Index: 1138908 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.3872. Min Act: -0.1700
Data Index: 1033127 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5010. Min Range: -2.5010
Max Act: 2.3709. Min Act: -0.1700
Data Index: 295795 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19