Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.7445. Min Act: -0.1700
Data Index: 24403 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.6350. Min Act: -0.1700
Data Index: 3739756 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.6350. Min Act: -0.1700
Data Index: 2014154 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.6350. Min Act: -0.1700
Data Index: 4726225 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.6350. Min Act: -0.1700
Data Index: 6411007 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.6194. Min Act: -0.1700
Data Index: 3645171 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.5881. Min Act: -0.1700
Data Index: 8419288 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.5881. Min Act: -0.1700
Data Index: 4875156 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.6194. Min Act: -0.1700
Data Index: 2668275 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.5568. Min Act: -0.1700
Data Index: 4264497 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.6037. Min Act: -0.1700
Data Index: 4861606 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.5724. Min Act: -0.1700
Data Index: 3646845 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.5881. Min Act: -0.1700
Data Index: 5675404 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.6037. Min Act: -0.1700
Data Index: 3142985 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.5724. Min Act: -0.1700
Data Index: 3392313 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.5724. Min Act: -0.1700
Data Index: 2668486 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.5724. Min Act: -0.1700
Data Index: 922279 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.5724. Min Act: -0.1700
Data Index: 3514492 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.5881. Min Act: -0.1700
Data Index: 3691773 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7445. Min Range: -3.7445
Max Act: 3.5568. Min Act: -0.1700
Data Index: 1117366 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19