Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1990 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.8563. Min Act: -0.1700
Data Index: 1414387 (Python Code)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.7288. Min Act: -0.1700
Data Index: 1125175 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.7448. Min Act: -0.1700
Data Index: 1547224 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.7288. Min Act: -0.1700
Data Index: 1559852 (Python Code)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.7288. Min Act: -0.1700
Data Index: 1314664 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6968. Min Act: -0.1700
Data Index: 1502613 (Python Code)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6808. Min Act: -0.1700
Data Index: 1625713 (Python Code)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6808. Min Act: -0.1700
Data Index: 1444362 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6648. Min Act: -0.1700
Data Index: 205067 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6808. Min Act: -0.1700
Data Index: 1397397 (Python Code)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6648. Min Act: -0.1700
Data Index: 1577723 (Python Code)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6487. Min Act: -0.1700
Data Index: 1474567 (Python Code)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6648. Min Act: -0.1700
Data Index: 1544854 (Python Code)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6487. Min Act: -0.1700
Data Index: 920352 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6487. Min Act: -0.1700
Data Index: 774586 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6487. Min Act: -0.1700
Data Index: 497930 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6648. Min Act: -0.1700
Data Index: 1117648 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6487. Min Act: -0.1700
Data Index: 267139 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6327. Min Act: -0.1700
Data Index: 1466368 (Python Code)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8563. Min Range: -2.8563
Max Act: 2.6327. Min Act: -0.1700
Data Index: 1511066 (Python Code)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19