Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 73 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.6174. Min Range: -5.6174
Max Act: 5.6174. Min Act: -0.1700
Data Index: 807446 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.9612. Min Act: -0.1700
Data Index: 975143 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.9612. Min Act: -0.1700
Data Index: 1343154 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.8674. Min Act: -0.1700
Data Index: 1314275 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.8362. Min Act: -0.1700
Data Index: 1272966 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.8049. Min Act: -0.1700
Data Index: 147710 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.8987. Min Act: -0.1700
Data Index: 979778 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.9612. Min Act: -0.1700
Data Index: 982490 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.8049. Min Act: -0.1700
Data Index: 1080187 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.8362. Min Act: -0.1700
Data Index: 1101646 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.8362. Min Act: -0.1700
Data Index: 749383 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.7737. Min Act: -0.1700
Data Index: 1494049 (Python Code)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.7737. Min Act: -0.1700
Data Index: 255104 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.8049. Min Act: -0.1700
Data Index: 529463 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.6799. Min Act: -0.1700
Data Index: 1329903 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.7737. Min Act: -0.1700
Data Index: 882517 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.7424. Min Act: -0.1700
Data Index: 913573 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.7424. Min Act: -0.1700
Data Index: 647785 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.7424. Min Act: -0.1700
Data Index: 187243 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6174. Min Range: -5.6174
Max Act: 4.6487. Min Act: -0.1700
Data Index: 598420 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19