Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7133. Min Range: -7.7133
Max Act: 7.7133. Min Act: -0.1700
Data Index: 7410982 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7133. Min Range: -7.7133
Max Act: 7.1820. Min Act: -0.1700
Data Index: 886068 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7133. Min Range: -7.7133
Max Act: 7.1508. Min Act: -0.1700
Data Index: 2108881 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7133. Min Range: -7.7133
Max Act: 7.1195. Min Act: -0.1700
Data Index: 8154963 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.9320. Min Act: -0.1700
Data Index: 5896444 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.9633. Min Act: -0.1700
Data Index: 5243685 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.8695. Min Act: -0.1700
Data Index: 2070193 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.8070. Min Act: -0.1700
Data Index: 50011 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.7445. Min Act: -0.1700
Data Index: 5212508 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.7133. Min Act: -0.1700
Data Index: 3690428 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.6820. Min Act: -0.1700
Data Index: 1684422 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.7133. Min Act: -0.1700
Data Index: 1439509 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.7133. Min Act: -0.1700
Data Index: 6013079 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.6508. Min Act: -0.1700
Data Index: 2211886 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.6820. Min Act: -0.1700
Data Index: 5906147 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.6820. Min Act: -0.1700
Data Index: 2109785 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.6820. Min Act: -0.1700
Data Index: 1219501 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.6820. Min Act: -0.1700
Data Index: 743655 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.6508. Min Act: -0.1700
Data Index: 6585451 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.6508. Min Act: -0.1700
Data Index: 3951091 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19