Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.6066. Min Act: -0.1700
Data Index: 634550 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.5583. Min Act: -0.1700
Data Index: 1566725 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.6066. Min Act: -0.1700
Data Index: 4558305 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.5421. Min Act: -0.1700
Data Index: 1882966 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.5260. Min Act: -0.1700
Data Index: 1882965 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.5260. Min Act: -0.1700
Data Index: 1882967 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.5098. Min Act: -0.1700
Data Index: 5476740 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.4611. Min Act: -0.1700
Data Index: 4632488 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.4936. Min Act: -0.1700
Data Index: 6832237 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.4611. Min Act: -0.1700
Data Index: 3022127 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.4123. Min Act: -0.1700
Data Index: 8024678 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.4286. Min Act: -0.1700
Data Index: 6819666 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.4286. Min Act: -0.1700
Data Index: 2463276 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.4123. Min Act: -0.1700
Data Index: 3502105 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.3960. Min Act: -0.1700
Data Index: 6645526 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.3960. Min Act: -0.1700
Data Index: 4144978 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.4123. Min Act: -0.1700
Data Index: 6788294 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.3633. Min Act: -0.1700
Data Index: 1523602 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.3797. Min Act: -0.1700
Data Index: 2477813 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6066. Min Range: -2.6066
Max Act: 2.3797. Min Act: -0.1700
Data Index: 5345326 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19