Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3444 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.5826. Min Act: -0.1700
Data Index: 4009947 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.5201. Min Act: -0.1700
Data Index: 4565611 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.5201. Min Act: -0.1700
Data Index: 2297597 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.5201. Min Act: -0.1700
Data Index: 5453315 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.5201. Min Act: -0.1700
Data Index: 5583108 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.4576. Min Act: -0.1700
Data Index: 3433903 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.4576. Min Act: -0.1700
Data Index: 721240 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.4576. Min Act: -0.1700
Data Index: 70086 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.4576. Min Act: -0.1700
Data Index: 5531412 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.4263. Min Act: -0.1700
Data Index: 8320238 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.4263. Min Act: -0.1700
Data Index: 1062490 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.4263. Min Act: -0.1700
Data Index: 6762375 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.4263. Min Act: -0.1700
Data Index: 6536881 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.4576. Min Act: -0.1700
Data Index: 6317224 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.4263. Min Act: -0.1699
Data Index: 5197104 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.3951. Min Act: -0.1700
Data Index: 2643512 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.3951. Min Act: -0.1700
Data Index: 5560362 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.3951. Min Act: -0.1700
Data Index: 292883 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.3951. Min Act: -0.1700
Data Index: 5014164 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5826. Min Range: -5.5826
Max Act: 5.3951. Min Act: -0.1700
Data Index: 1062489 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19