Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 122 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.8114. Min Act: -0.1700
Data Index: 6181549 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.6552. Min Act: -0.1700
Data Index: 3212732 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.6239. Min Act: -0.1700
Data Index: 4365810 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.4989. Min Act: -0.1700
Data Index: 6463925 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.4677. Min Act: -0.1700
Data Index: 7077430 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.4364. Min Act: -0.1700
Data Index: 4319168 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.4364. Min Act: -0.1700
Data Index: 7854064 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.4364. Min Act: -0.1700
Data Index: 4365809 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.4052. Min Act: -0.1700
Data Index: 5048760 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.4052. Min Act: -0.1700
Data Index: 4407973 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.4052. Min Act: -0.1700
Data Index: 7077427 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.4052. Min Act: -0.1700
Data Index: 4407978 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.3739. Min Act: -0.1700
Data Index: 4527328 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.3427. Min Act: -0.1700
Data Index: 4325407 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.3114. Min Act: -0.1700
Data Index: 1113874 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.3114. Min Act: -0.1700
Data Index: 6181590 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.3114. Min Act: -0.1700
Data Index: 2523696 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.3427. Min Act: -0.1700
Data Index: 5612567 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.3427. Min Act: -0.1700
Data Index: 6122496 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8114. Min Range: -4.8114
Max Act: 4.3427. Min Act: -0.1700
Data Index: 5885501 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19