Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5575 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.6795. Min Act: -0.1700
Data Index: 7283608 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.5545. Min Act: -0.1700
Data Index: 7281473 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.5545. Min Act: -0.1700
Data Index: 188277 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.4608. Min Act: -0.1700
Data Index: 6123464 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.4295. Min Act: -0.1700
Data Index: 4053911 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.3670. Min Act: -0.1700
Data Index: 1515470 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.3670. Min Act: -0.1700
Data Index: 85989 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.3670. Min Act: -0.1700
Data Index: 1584870 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.3670. Min Act: -0.1700
Data Index: 8111216 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.3358. Min Act: -0.1700
Data Index: 5187872 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.3358. Min Act: -0.1700
Data Index: 3474437 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.2733. Min Act: -0.1700
Data Index: 2574501 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.2733. Min Act: -0.1700
Data Index: 8298922 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.2733. Min Act: -0.1700
Data Index: 786721 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.2420. Min Act: -0.1700
Data Index: 1124244 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.2108. Min Act: -0.1700
Data Index: 7993093 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.2420. Min Act: -0.1700
Data Index: 694877 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.2420. Min Act: -0.1700
Data Index: 4428752 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.2420. Min Act: -0.1700
Data Index: 3186634 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6795. Min Range: -4.6795
Max Act: 4.2420. Min Act: -0.1700
Data Index: 7803451 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19