Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 363 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0436. Min Range: -2.0436
Max Act: 2.0436. Min Act: -0.1700
Data Index: 1158473 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0436. Min Range: -2.0436
Max Act: 2.0436. Min Act: -0.1700
Data Index: 419904 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.9761. Min Act: -0.1700
Data Index: 3507712 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.9761. Min Act: -0.1700
Data Index: 2505431 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.9336. Min Act: -0.1700
Data Index: 6014643 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.9251. Min Act: -0.1700
Data Index: 4369747 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.9421. Min Act: -0.1700
Data Index: 671953 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.9336. Min Act: -0.1700
Data Index: 8619987 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.9166. Min Act: -0.1700
Data Index: 6839355 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.9251. Min Act: -0.1700
Data Index: 5447798 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.8996. Min Act: -0.1700
Data Index: 7663499 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.9081. Min Act: -0.1700
Data Index: 7958888 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.8996. Min Act: -0.1700
Data Index: 2356546 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.8910. Min Act: -0.1700
Data Index: 7686055 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.8996. Min Act: -0.1700
Data Index: 3289875 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.8996. Min Act: -0.1700
Data Index: 5547002 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.8996. Min Act: -0.1699
Data Index: 3543790 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.8825. Min Act: -0.1699
Data Index: 6445175 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.8740. Min Act: -0.1700
Data Index: 4413324 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0436. Min Range: -2.0436
Max Act: 1.8825. Min Act: -0.1700
Data Index: 3065301 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19