Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 864 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.7507. Min Act: -0.1700
Data Index: 4115973 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.6882. Min Act: -0.1700
Data Index: 6670213 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.6570. Min Act: -0.1700
Data Index: 2050513 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5945. Min Act: -0.1700
Data Index: 2248099 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5632. Min Act: -0.1700
Data Index: 2424437 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5632. Min Act: -0.1700
Data Index: 4489817 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5945. Min Act: -0.1700
Data Index: 2616398 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5320. Min Act: -0.1700
Data Index: 4076898 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5007. Min Act: -0.1700
Data Index: 69099 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4695. Min Act: -0.1700
Data Index: 6812278 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4695. Min Act: -0.1700
Data Index: 4242027 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4382. Min Act: -0.1700
Data Index: 6312026 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4382. Min Act: -0.1700
Data Index: 6538734 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4070. Min Act: -0.1700
Data Index: 4952379 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4070. Min Act: -0.1700
Data Index: 4869930 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4382. Min Act: -0.1700
Data Index: 2933023 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4070. Min Act: -0.1700
Data Index: 2561123 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4382. Min Act: -0.1700
Data Index: 7256086 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4070. Min Act: -0.1700
Data Index: 1450141 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3757. Min Act: -0.1700
Data Index: 3892836 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19