Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3877 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1266. Min Range: -4.1266
Max Act: 4.1266. Min Act: -0.1700
Data Index: 5437792 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1266. Min Range: -4.1266
Max Act: 4.0954. Min Act: -0.1700
Data Index: 892268 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1266. Min Range: -4.1266
Max Act: 4.0329. Min Act: -0.1700
Data Index: 8096657 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1266. Min Range: -4.1266
Max Act: 4.0329. Min Act: -0.1700
Data Index: 8683146 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1266. Min Range: -4.1266
Max Act: 4.0016. Min Act: -0.1700
Data Index: 6436754 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1266. Min Range: -4.1266
Max Act: 4.0016. Min Act: -0.1700
Data Index: 4543379 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1266. Min Range: -4.1266
Max Act: 3.9703. Min Act: -0.1700
Data Index: 3824044 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1266. Min Range: -4.1266
Max Act: 3.9703. Min Act: -0.1700
Data Index: 8274803 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1266. Min Range: -4.1266
Max Act: 4.0016. Min Act: -0.1700
Data Index: 712545 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1266. Min Range: -4.1266
Max Act: 3.9391. Min Act: -0.1700
Data Index: 1975303 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1266. Min Range: -4.1266
Max Act: 3.9703. Min Act: -0.1700
Data Index: 993570 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1266. Min Range: -4.1266
Max Act: 3.9391. Min Act: -0.1700
Data Index: 2629476 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1266. Min Range: -4.1266
Max Act: 3.9078. Min Act: -0.1700
Data Index: 1860583 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1266. Min Range: -4.1266
Max Act: 3.9078. Min Act: -0.1700
Data Index: 4318751 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1266. Min Range: -4.1266
Max Act: 3.9078. Min Act: -0.1700
Data Index: 8645697 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1266. Min Range: -4.1266
Max Act: 3.9078. Min Act: -0.1700
Data Index: 3921768 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1266. Min Range: -4.1266
Max Act: 3.9078. Min Act: -0.1700
Data Index: 5429742 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1266. Min Range: -4.1266
Max Act: 3.9078. Min Act: -0.1700
Data Index: 3917710 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1266. Min Range: -4.1266
Max Act: 3.9078. Min Act: -0.1700
Data Index: 2961938 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1266. Min Range: -4.1266
Max Act: 3.9078. Min Act: -0.1700
Data Index: 3545224 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19