Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1319 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.2961. Min Act: -0.1700
Data Index: 282513 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.2961. Min Act: -0.1700
Data Index: 182279 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.2302. Min Act: -0.1700
Data Index: 1051609 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.2302. Min Act: -0.1700
Data Index: 231152 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.2302. Min Act: -0.1700
Data Index: 1599415 (Python Code)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.2136. Min Act: -0.1700
Data Index: 346452 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.1804. Min Act: -0.1700
Data Index: 1237204 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.1970. Min Act: -0.1700
Data Index: 705554 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.2136. Min Act: -0.1700
Data Index: 801416 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.1804. Min Act: -0.1700
Data Index: 315744 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.1638. Min Act: -0.1700
Data Index: 311768 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.1472. Min Act: -0.1700
Data Index: 1055926 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.1472. Min Act: -0.1700
Data Index: 1270315 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.1472. Min Act: -0.1700
Data Index: 911470 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.1472. Min Act: -0.1700
Data Index: 1085620 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.1638. Min Act: -0.1700
Data Index: 471663 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.1472. Min Act: -0.1700
Data Index: 441730 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.1472. Min Act: -0.1700
Data Index: 1276349 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.1472. Min Act: -0.1700
Data Index: 1118178 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2961. Min Range: -2.2961
Max Act: 2.1138. Min Act: -0.1700
Data Index: 1166362 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19