Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 155 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0699. Min Range: -4.0699
Max Act: 4.0699. Min Act: -0.1700
Data Index: 49659 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0699. Min Range: -4.0699
Max Act: 4.0387. Min Act: -0.1700
Data Index: 302499 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0699. Min Range: -4.0699
Max Act: 4.0387. Min Act: -0.1700
Data Index: 958188 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0699. Min Range: -4.0699
Max Act: 4.0074. Min Act: -0.1700
Data Index: 779014 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0699. Min Range: -4.0699
Max Act: 4.0387. Min Act: -0.1700
Data Index: 672625 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0699. Min Range: -4.0699
Max Act: 4.0074. Min Act: -0.1700
Data Index: 967647 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0699. Min Range: -4.0699
Max Act: 4.0074. Min Act: -0.1700
Data Index: 1029597 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0699. Min Range: -4.0699
Max Act: 3.9605. Min Act: -0.1700
Data Index: 180279 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0699. Min Range: -4.0699
Max Act: 3.9605. Min Act: -0.1700
Data Index: 812192 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0699. Min Range: -4.0699
Max Act: 3.9605. Min Act: -0.1700
Data Index: 510026 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0699. Min Range: -4.0699
Max Act: 3.9761. Min Act: -0.1700
Data Index: 1246203 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0699. Min Range: -4.0699
Max Act: 3.9449. Min Act: -0.1700
Data Index: 456966 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0699. Min Range: -4.0699
Max Act: 3.9292. Min Act: -0.1700
Data Index: 245058 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0699. Min Range: -4.0699
Max Act: 3.9449. Min Act: -0.1700
Data Index: 1148713 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0699. Min Range: -4.0699
Max Act: 3.9449. Min Act: -0.1700
Data Index: 676430 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0699. Min Range: -4.0699
Max Act: 3.9136. Min Act: -0.1700
Data Index: 1125134 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0699. Min Range: -4.0699
Max Act: 3.9136. Min Act: -0.1700
Data Index: 880474 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0699. Min Range: -4.0699
Max Act: 3.8980. Min Act: -0.1700
Data Index: 651001 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0699. Min Range: -4.0699
Max Act: 3.8980. Min Act: -0.1700
Data Index: 105466 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0699. Min Range: -4.0699
Max Act: 3.9136. Min Act: -0.1700
Data Index: 615726 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19