Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1466 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.7893. Min Act: -0.1700
Data Index: 409027 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.6935. Min Act: -0.1700
Data Index: 1190169 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.6775. Min Act: -0.1700
Data Index: 728517 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.6294. Min Act: -0.1700
Data Index: 831500 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5972. Min Act: -0.1700
Data Index: 755544 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.6133. Min Act: -0.1700
Data Index: 272932 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5972. Min Act: -0.1700
Data Index: 882094 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.6133. Min Act: -0.1700
Data Index: 615527 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5972. Min Act: -0.1700
Data Index: 341618 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5972. Min Act: -0.1700
Data Index: 593345 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5972. Min Act: -0.1700
Data Index: 1276385 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5811. Min Act: -0.1700
Data Index: 99051 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5650. Min Act: -0.1700
Data Index: 321630 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5811. Min Act: -0.1700
Data Index: 1186352 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5811. Min Act: -0.1700
Data Index: 946064 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5811. Min Act: -0.1700
Data Index: 514665 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5650. Min Act: -0.1700
Data Index: 645035 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5650. Min Act: -0.1700
Data Index: 773466 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5650. Min Act: -0.1700
Data Index: 1303147 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7893. Min Range: -2.7893
Max Act: 2.5650. Min Act: -0.1700
Data Index: 542540 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19