Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 522 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0713. Min Range: -4.0713
Max Act: 4.0713. Min Act: -0.1700
Data Index: 206393 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0713. Min Range: -4.0713
Max Act: 4.0088. Min Act: -0.1700
Data Index: 2467572 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0713. Min Range: -4.0713
Max Act: 4.0401. Min Act: -0.1700
Data Index: 4895634 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.9307. Min Act: -0.1700
Data Index: 3989304 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.9463. Min Act: -0.1700
Data Index: 5998150 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.8838. Min Act: -0.1700
Data Index: 5441184 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.8525. Min Act: -0.1700
Data Index: 6486296 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.8681. Min Act: -0.1700
Data Index: 8208098 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.8681. Min Act: -0.1700
Data Index: 1857997 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.8681. Min Act: -0.1700
Data Index: 751465 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.8369. Min Act: -0.1700
Data Index: 6782477 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.8369. Min Act: -0.1700
Data Index: 7143241 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.7899. Min Act: -0.1700
Data Index: 4511877 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.8056. Min Act: -0.1700
Data Index: 7266151 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.7899. Min Act: -0.1700
Data Index: 3998021 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.7899. Min Act: -0.1700
Data Index: 3607218 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.8056. Min Act: -0.1700
Data Index: 45746 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.8212. Min Act: -0.1700
Data Index: 7253473 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.7899. Min Act: -0.1700
Data Index: 1863358 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0713. Min Range: -4.0713
Max Act: 3.7899. Min Act: -0.1700
Data Index: 6500196 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19