Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3037 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.4406. Min Act: -0.1700
Data Index: 4658218 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.4406. Min Act: -0.1700
Data Index: 1404573 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3935. Min Act: -0.1700
Data Index: 2631513 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3935. Min Act: -0.1700
Data Index: 3132456 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3935. Min Act: -0.1700
Data Index: 8195240 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3622. Min Act: -0.1700
Data Index: 3464600 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3622. Min Act: -0.1700
Data Index: 8086567 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3935. Min Act: -0.1700
Data Index: 3605036 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3622. Min Act: -0.1700
Data Index: 5573397 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3465. Min Act: -0.1700
Data Index: 5777143 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3622. Min Act: -0.1700
Data Index: 895285 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3308. Min Act: -0.1700
Data Index: 4232794 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3465. Min Act: -0.1700
Data Index: 265493 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3308. Min Act: -0.1700
Data Index: 5331514 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3308. Min Act: -0.1700
Data Index: 5590531 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.2994. Min Act: -0.1700
Data Index: 4675012 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3151. Min Act: -0.1700
Data Index: 2087069 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3308. Min Act: -0.1700
Data Index: 7702915 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3465. Min Act: -0.1700
Data Index: 4358715 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4406. Min Range: -3.4406
Max Act: 3.3151. Min Act: -0.1700
Data Index: 3605035 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19