Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2838 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.6400. Min Act: -0.1700
Data Index: 2367720 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.6349. Min Act: -0.1700
Data Index: 4147185 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.6203. Min Act: -0.1700
Data Index: 112793 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.6054. Min Act: -0.1700
Data Index: 2446817 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.5974. Min Act: -0.1700
Data Index: 2723725 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.5718. Min Act: -0.1700
Data Index: 1410762 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.5450. Min Act: -0.1700
Data Index: 1410763 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.4910. Min Act: -0.1700
Data Index: 6448025 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.4923. Min Act: -0.1700
Data Index: 7694107 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.4614. Min Act: -0.1700
Data Index: 5986793 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.4466. Min Act: -0.1700
Data Index: 3760238 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.4280. Min Act: -0.1700
Data Index: 4000250 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.4178. Min Act: -0.1700
Data Index: 1045726 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.4290. Min Act: -0.1700
Data Index: 6875395 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.3907. Min Act: -0.1700
Data Index: 4435002 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.4100. Min Act: -0.1700
Data Index: 7571760 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.3853. Min Act: -0.1700
Data Index: 228319 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.3667. Min Act: -0.1700
Data Index: 5393298 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.3869. Min Act: -0.1700
Data Index: 4113619 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.6400. Min Range: -3.6400
Max Act: 3.3774. Min Act: -0.1700
Data Index: 952476 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full textTruncated
Full Text #19