Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 902 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.8362. Min Act: -0.1700
Data Index: 2762986 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7580. Min Act: -0.1700
Data Index: 3526208 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7267. Min Act: -0.1700
Data Index: 1292527 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6955. Min Act: -0.1700
Data Index: 5945038 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6172. Min Act: -0.1700
Data Index: 2891614 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6016. Min Act: -0.1700
Data Index: 1173830 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5859. Min Act: -0.1700
Data Index: 4679152 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5546. Min Act: -0.1700
Data Index: 5878309 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5390. Min Act: -0.1700
Data Index: 8744932 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5233. Min Act: -0.1700
Data Index: 6157890 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5076. Min Act: -0.1700
Data Index: 8049692 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5076. Min Act: -0.1700
Data Index: 7782656 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.4763. Min Act: -0.1700
Data Index: 1883110 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5233. Min Act: -0.1700
Data Index: 8672712 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.4450. Min Act: -0.1700
Data Index: 1360720 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.4920. Min Act: -0.1700
Data Index: 7767165 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.4763. Min Act: -0.1700
Data Index: 8427737 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.4920. Min Act: -0.1700
Data Index: 4783588 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.4606. Min Act: -0.1700
Data Index: 7888451 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.4606. Min Act: -0.1700
Data Index: 4457452 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19