Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.8435. Min Act: -0.1700
Data Index: 8784797 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.7810. Min Act: -0.1700
Data Index: 7498860 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.8123. Min Act: -0.1700
Data Index: 3877740 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.7185. Min Act: -0.1700
Data Index: 6366529 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.7185. Min Act: -0.1700
Data Index: 6446644 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.6873. Min Act: -0.1700
Data Index: 8000808 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.6873. Min Act: -0.1700
Data Index: 5618000 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.5623. Min Act: -0.1700
Data Index: 6167731 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.5310. Min Act: -0.1700
Data Index: 3394528 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.4998. Min Act: -0.1700
Data Index: 4618409 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.4685. Min Act: -0.1700
Data Index: 4700774 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.4685. Min Act: -0.1700
Data Index: 5656094 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.4373. Min Act: -0.1700
Data Index: 2156161 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.4685. Min Act: -0.1700
Data Index: 3436397 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.4685. Min Act: -0.1700
Data Index: 1947957 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.4373. Min Act: -0.1700
Data Index: 1162944 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.4373. Min Act: -0.1700
Data Index: 8756942 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.4060. Min Act: -0.1700
Data Index: 5302410 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.4060. Min Act: -0.1700
Data Index: 8581000 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8435. Min Range: -5.8435
Max Act: 5.4373. Min Act: -0.1700
Data Index: 5036794 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19