Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7208. Min Range: -6.7208
Max Act: 6.7208. Min Act: -0.1700
Data Index: 5124288 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7208. Min Range: -6.7208
Max Act: 6.0021. Min Act: -0.1700
Data Index: 4646203 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7208. Min Range: -6.7208
Max Act: 6.3771. Min Act: -0.1700
Data Index: 4058857 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7208. Min Range: -6.7208
Max Act: 6.2521. Min Act: -0.1700
Data Index: 4110680 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7208. Min Range: -6.7208
Max Act: 6.1271. Min Act: -0.1700
Data Index: 6726495 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7208. Min Range: -6.7208
Max Act: 6.0646. Min Act: -0.1700
Data Index: 7553946 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7208. Min Range: -6.7208
Max Act: 6.0333. Min Act: -0.1700
Data Index: 7023131 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7208. Min Range: -6.7208
Max Act: 6.0646. Min Act: -0.1700
Data Index: 4298840 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7208. Min Range: -6.7208
Max Act: 6.0021. Min Act: -0.1700
Data Index: 2946175 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7208. Min Range: -6.7208
Max Act: 5.9708. Min Act: -0.1700
Data Index: 471284 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7208. Min Range: -6.7208
Max Act: 6.0333. Min Act: -0.1700
Data Index: 4656583 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7208. Min Range: -6.7208
Max Act: 6.0021. Min Act: -0.1700
Data Index: 4298751 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7208. Min Range: -6.7208
Max Act: 5.9708. Min Act: -0.1700
Data Index: 6101934 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7208. Min Range: -6.7208
Max Act: 5.9396. Min Act: -0.1700
Data Index: 7220357 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7208. Min Range: -6.7208
Max Act: 6.0021. Min Act: -0.1700
Data Index: 4828072 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7208. Min Range: -6.7208
Max Act: 5.9396. Min Act: -0.1700
Data Index: 5067630 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7208. Min Range: -6.7208
Max Act: 5.9396. Min Act: -0.1700
Data Index: 8420569 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7208. Min Range: -6.7208
Max Act: 5.9396. Min Act: -0.1700
Data Index: 810995 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7208. Min Range: -6.7208
Max Act: 5.9083. Min Act: -0.1700
Data Index: 4908021 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7208. Min Range: -6.7208
Max Act: 5.8458. Min Act: -0.1700
Data Index: 5271401 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19