Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 51 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.5124. Min Act: -0.1700
Data Index: 325167 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.3561. Min Act: -0.1700
Data Index: 633941 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.3249. Min Act: -0.1700
Data Index: 5348666 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.3249. Min Act: -0.1700
Data Index: 2928218 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.2624. Min Act: -0.1700
Data Index: 7260800 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.2624. Min Act: -0.1700
Data Index: 7776021 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.2624. Min Act: -0.1700
Data Index: 2840920 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.2624. Min Act: -0.1700
Data Index: 7851637 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1686. Min Act: -0.1700
Data Index: 6473767 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1686. Min Act: -0.1700
Data Index: 4679104 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1374. Min Act: -0.1700
Data Index: 3592515 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1374. Min Act: -0.1700
Data Index: 7717785 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1374. Min Act: -0.1700
Data Index: 3289069 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1374. Min Act: -0.1700
Data Index: 8310393 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1061. Min Act: -0.1700
Data Index: 1398744 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1374. Min Act: -0.1700
Data Index: 7717740 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1061. Min Act: -0.1700
Data Index: 3944901 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1061. Min Act: -0.1700
Data Index: 1649501 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1061. Min Act: -0.1700
Data Index: 3377382 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.0749. Min Act: -0.1700
Data Index: 64634 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19