Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3717 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0885. Min Range: -4.0885
Max Act: 4.0885. Min Act: -0.1700
Data Index: 5756204 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.9947. Min Act: -0.1700
Data Index: 1562400 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.9009. Min Act: -0.1700
Data Index: 1287068 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.7445. Min Act: -0.1700
Data Index: 1311420 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.7132. Min Act: -0.1700
Data Index: 4126824 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.6350. Min Act: -0.1700
Data Index: 5325255 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.6037. Min Act: -0.1700
Data Index: 5927618 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.5724. Min Act: -0.1700
Data Index: 4788654 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.5724. Min Act: -0.1700
Data Index: 2615432 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.5568. Min Act: -0.1700
Data Index: 840732 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.5724. Min Act: -0.1700
Data Index: 4297224 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.5411. Min Act: -0.1700
Data Index: 897479 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.5098. Min Act: -0.1700
Data Index: 8074388 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.4785. Min Act: -0.1700
Data Index: 6936084 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.5098. Min Act: -0.1700
Data Index: 6209274 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.4785. Min Act: -0.1700
Data Index: 3364324 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.4785. Min Act: -0.1700
Data Index: 7093294 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.4941. Min Act: -0.1700
Data Index: 1177880 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.4628. Min Act: -0.1700
Data Index: 2234433 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0885. Min Range: -4.0885
Max Act: 3.4785. Min Act: -0.1700
Data Index: 8471172 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19