Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 444 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8874. Min Act: -0.1700
Data Index: 8330295 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.9500. Min Act: -0.1700
Data Index: 4469458 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8562. Min Act: -0.1700
Data Index: 6509471 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.9187. Min Act: -0.1700
Data Index: 2212028 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8562. Min Act: -0.1700
Data Index: 7846239 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8874. Min Act: -0.1700
Data Index: 5896254 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8562. Min Act: -0.1700
Data Index: 2780308 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.7936. Min Act: -0.1700
Data Index: 7707203 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8249. Min Act: -0.1700
Data Index: 949937 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8249. Min Act: -0.1700
Data Index: 7455723 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8562. Min Act: -0.1700
Data Index: 6609234 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8562. Min Act: -0.1700
Data Index: 2844135 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8562. Min Act: -0.1700
Data Index: 7807263 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.7936. Min Act: -0.1700
Data Index: 3304797 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8562. Min Act: -0.1700
Data Index: 7840818 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8562. Min Act: -0.1700
Data Index: 6669479 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.7623. Min Act: -0.1700
Data Index: 8153723 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8249. Min Act: -0.1700
Data Index: 4302837 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.8249. Min Act: -0.1700
Data Index: 2675511 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.7936. Min Act: -0.1700
Data Index: 7454224 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19