Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1456 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.2732. Min Act: -0.1700
Data Index: 1029315 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.2107. Min Act: -0.1700
Data Index: 6045176 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.2419. Min Act: -0.1700
Data Index: 3363623 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.1169. Min Act: -0.1700
Data Index: 5946106 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.1481. Min Act: -0.1700
Data Index: 445423 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.1169. Min Act: -0.1700
Data Index: 3286506 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.1169. Min Act: -0.1700
Data Index: 3645862 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.1169. Min Act: -0.1700
Data Index: 4478458 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.0856. Min Act: -0.1700
Data Index: 5208319 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.0856. Min Act: -0.1700
Data Index: 4883336 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.0856. Min Act: -0.1700
Data Index: 5592822 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.0231. Min Act: -0.1700
Data Index: 5561464 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.0231. Min Act: -0.1700
Data Index: 3249783 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2732. Min Range: -4.2732
Max Act: 4.0231. Min Act: -0.1700
Data Index: 7326010 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2732. Min Range: -4.2732
Max Act: 3.9606. Min Act: -0.1700
Data Index: 2770086 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2732. Min Range: -4.2732
Max Act: 3.9919. Min Act: -0.1700
Data Index: 3196559 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2732. Min Range: -4.2732
Max Act: 3.9606. Min Act: -0.1700
Data Index: 845866 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2732. Min Range: -4.2732
Max Act: 3.9293. Min Act: -0.1700
Data Index: 975122 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2732. Min Range: -4.2732
Max Act: 3.9293. Min Act: -0.1700
Data Index: 5568684 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2732. Min Range: -4.2732
Max Act: 3.8981. Min Act: -0.1700
Data Index: 1018272 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19