Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2644 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.7991. Min Act: -0.1700
Data Index: 6876297 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.7991. Min Act: -0.1700
Data Index: 7207475 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.7679. Min Act: -0.1700
Data Index: 1858686 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.7054. Min Act: -0.1700
Data Index: 2145969 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.7366. Min Act: -0.1700
Data Index: 1763610 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.7054. Min Act: -0.1700
Data Index: 2822293 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.6741. Min Act: -0.1700
Data Index: 6983395 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.6741. Min Act: -0.1700
Data Index: 100108 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.7054. Min Act: -0.1700
Data Index: 8823051 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.6741. Min Act: -0.1700
Data Index: 1351304 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.6429. Min Act: -0.1700
Data Index: 5972079 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.6429. Min Act: -0.1700
Data Index: 7571412 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.6429. Min Act: -0.1700
Data Index: 5574935 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.6116. Min Act: -0.1700
Data Index: 5838792 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.6116. Min Act: -0.1700
Data Index: 555453 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.5804. Min Act: -0.1700
Data Index: 4074592 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.5804. Min Act: -0.1700
Data Index: 544704 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.5804. Min Act: -0.1700
Data Index: 3304494 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.5491. Min Act: -0.1700
Data Index: 2822294 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7991. Min Range: -5.7991
Max Act: 5.5491. Min Act: -0.1700
Data Index: 3885446 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19