Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 51 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.5894. Min Act: -0.1700
Data Index: 8452822 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.5883. Min Act: -0.1700
Data Index: 8731837 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.4441. Min Act: -0.1700
Data Index: 2706143 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.2319. Min Act: -0.1700
Data Index: 537185 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.2230. Min Act: -0.1700
Data Index: 3151783 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.1360. Min Act: -0.1700
Data Index: 5232633 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.1280. Min Act: -0.1700
Data Index: 6120689 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.0894. Min Act: -0.1700
Data Index: 3574286 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.1016. Min Act: -0.1700
Data Index: 2311603 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.0498. Min Act: -0.1700
Data Index: 2893681 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.0460. Min Act: -0.1700
Data Index: 3596509 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.0367. Min Act: -0.1700
Data Index: 5769781 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.0158. Min Act: -0.1700
Data Index: 4619176 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 5.5894. Min Range: -5.5894
Max Act: 5.0011. Min Act: -0.1700
Data Index: 6656468 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 5.5894. Min Range: -5.5894
Max Act: 4.9902. Min Act: -0.1700
Data Index: 7856677 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 5.5894. Min Range: -5.5894
Max Act: 4.9552. Min Act: -0.1700
Data Index: 4716679 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 5.5894. Min Range: -5.5894
Max Act: 4.9324. Min Act: -0.1700
Data Index: 3915987 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 5.5894. Min Range: -5.5894
Max Act: 4.9048. Min Act: -0.1700
Data Index: 4500583 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 5.5894. Min Range: -5.5894
Max Act: 4.9387. Min Act: -0.1700
Data Index: 5933142 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 5.5894. Min Range: -5.5894
Max Act: 4.9157. Min Act: -0.1700
Data Index: 3771307 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full textTruncated
Full Text #19