Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3174 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0386. Min Range: -8.0386
Max Act: 8.0386. Min Act: -0.1700
Data Index: 4265431 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.8511. Min Act: -0.1700
Data Index: 5479036 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.7886. Min Act: -0.1700
Data Index: 488764 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.4761. Min Act: -0.1700
Data Index: 8454491 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.4136. Min Act: -0.1700
Data Index: 8551167 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.2573. Min Act: -0.1700
Data Index: 6889140 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.2261. Min Act: -0.1700
Data Index: 7291501 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.1636. Min Act: -0.1700
Data Index: 1089554 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.1323. Min Act: -0.1700
Data Index: 4112297 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.0698. Min Act: -0.1700
Data Index: 3229531 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.0386. Min Act: -0.1700
Data Index: 5568348 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.1011. Min Act: -0.1700
Data Index: 4179017 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.0698. Min Act: -0.1700
Data Index: 8035024 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.0698. Min Act: -0.1700
Data Index: 2517763 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0386. Min Range: -8.0386
Max Act: 6.9761. Min Act: -0.1700
Data Index: 7967523 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0386. Min Range: -8.0386
Max Act: 6.9761. Min Act: -0.1700
Data Index: 6137543 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0386. Min Range: -8.0386
Max Act: 6.9761. Min Act: -0.1700
Data Index: 7911025 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.0386. Min Act: -0.1700
Data Index: 2784017 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0386. Min Range: -8.0386
Max Act: 7.0073. Min Act: -0.1700
Data Index: 5345182 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0386. Min Range: -8.0386
Max Act: 6.9761. Min Act: -0.1700
Data Index: 6652780 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19