Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2122 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.3162. Min Act: -0.1700
Data Index: 2212900 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2835. Min Act: -0.1700
Data Index: 4657536 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2695. Min Act: -0.1700
Data Index: 5414114 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2686. Min Act: -0.1700
Data Index: 7781150 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2651. Min Act: -0.1700
Data Index: 7902778 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2666. Min Act: -0.1700
Data Index: 6123151 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2598. Min Act: -0.1700
Data Index: 1715439 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2487. Min Act: -0.1700
Data Index: 2455874 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2540. Min Act: -0.1700
Data Index: 3178362 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2472. Min Act: -0.1700
Data Index: 6136455 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2570. Min Act: -0.1700
Data Index: 6386898 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2526. Min Act: -0.1700
Data Index: 3181241 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2155. Min Act: -0.1700
Data Index: 8432408 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2118. Min Act: -0.1700
Data Index: 1526160 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.1966. Min Act: -0.1700
Data Index: 7222619 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2045. Min Act: -0.1700
Data Index: 7658901 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.1831. Min Act: -0.1700
Data Index: 165020 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2168. Min Act: -0.1700
Data Index: 2494698 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2100. Min Act: -0.1700
Data Index: 2934758 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2016. Min Act: -0.1700
Data Index: 3282205 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full textTruncated
Full Text #19