Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 947 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2953. Min Range: -5.2953
Max Act: 5.2953. Min Act: -0.1700
Data Index: 5560163 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2953. Min Range: -5.2953
Max Act: 5.2640. Min Act: -0.1700
Data Index: 519263 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2953. Min Range: -5.2953
Max Act: 5.2328. Min Act: -0.1700
Data Index: 7660155 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2953. Min Range: -5.2953
Max Act: 5.1078. Min Act: -0.1700
Data Index: 15913 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2953. Min Range: -5.2953
Max Act: 5.0765. Min Act: -0.1700
Data Index: 2913649 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2953. Min Range: -5.2953
Max Act: 5.0140. Min Act: -0.1700
Data Index: 1093957 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2953. Min Range: -5.2953
Max Act: 5.0140. Min Act: -0.1700
Data Index: 3855847 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2953. Min Range: -5.2953
Max Act: 4.9828. Min Act: -0.1700
Data Index: 721059 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2953. Min Range: -5.2953
Max Act: 5.0140. Min Act: -0.1700
Data Index: 5149128 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2953. Min Range: -5.2953
Max Act: 5.0140. Min Act: -0.1700
Data Index: 3235734 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2953. Min Range: -5.2953
Max Act: 5.0140. Min Act: -0.1700
Data Index: 5015164 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2953. Min Range: -5.2953
Max Act: 4.9828. Min Act: -0.1700
Data Index: 4530994 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2953. Min Range: -5.2953
Max Act: 5.0140. Min Act: -0.1700
Data Index: 8790338 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2953. Min Range: -5.2953
Max Act: 4.9828. Min Act: -0.1700
Data Index: 2316432 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2953. Min Range: -5.2953
Max Act: 4.9828. Min Act: -0.1700
Data Index: 7481276 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2953. Min Range: -5.2953
Max Act: 5.0140. Min Act: -0.1700
Data Index: 5981680 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2953. Min Range: -5.2953
Max Act: 4.9515. Min Act: -0.1700
Data Index: 1384472 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2953. Min Range: -5.2953
Max Act: 4.9828. Min Act: -0.1700
Data Index: 8308421 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2953. Min Range: -5.2953
Max Act: 4.9515. Min Act: -0.1700
Data Index: 2568451 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2953. Min Range: -5.2953
Max Act: 4.9203. Min Act: -0.1700
Data Index: 2129208 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19