Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 415 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.2715. Min Act: -0.1700
Data Index: 6233689 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.1772. Min Act: -0.1700
Data Index: 6622233 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.1615. Min Act: -0.1700
Data Index: 4608308 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.1457. Min Act: -0.1700
Data Index: 2224217 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.1615. Min Act: -0.1700
Data Index: 6901331 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.0827. Min Act: -0.1700
Data Index: 8068433 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.0827. Min Act: -0.1700
Data Index: 3765120 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.0670. Min Act: -0.1700
Data Index: 4458216 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.0827. Min Act: -0.1700
Data Index: 7284455 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.0670. Min Act: -0.1700
Data Index: 5556128 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.0512. Min Act: -0.1700
Data Index: 2126276 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.0512. Min Act: -0.1700
Data Index: 2824536 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.0038. Min Act: -0.1700
Data Index: 7201171 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2715. Min Range: -3.2715
Max Act: 2.9880. Min Act: -0.1700
Data Index: 7326587 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2715. Min Range: -3.2715
Max Act: 2.9880. Min Act: -0.1700
Data Index: 3311982 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2715. Min Range: -3.2715
Max Act: 2.9880. Min Act: -0.1700
Data Index: 6760770 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2715. Min Range: -3.2715
Max Act: 3.0038. Min Act: -0.1700
Data Index: 5040728 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2715. Min Range: -3.2715
Max Act: 2.9880. Min Act: -0.1700
Data Index: 2391785 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2715. Min Range: -3.2715
Max Act: 2.9722. Min Act: -0.1700
Data Index: 6427191 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2715. Min Range: -3.2715
Max Act: 2.9880. Min Act: -0.1700
Data Index: 3500734 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19