Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1619 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0161. Min Range: -5.0161
Max Act: 5.0161. Min Act: -0.1700
Data Index: 3907618 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.8599. Min Act: -0.1700
Data Index: 21653 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7661. Min Act: -0.1700
Data Index: 8259373 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.6411. Min Act: -0.1700
Data Index: 4659485 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.5473. Min Act: -0.1700
Data Index: 4406005 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.5473. Min Act: -0.1700
Data Index: 7466643 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.5473. Min Act: -0.1700
Data Index: 7972352 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.5161. Min Act: -0.1700
Data Index: 1108872 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.4848. Min Act: -0.1700
Data Index: 6581567 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.4848. Min Act: -0.1700
Data Index: 5241686 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.4848. Min Act: -0.1700
Data Index: 3477203 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.4848. Min Act: -0.1700
Data Index: 2430842 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.5161. Min Act: -0.1700
Data Index: 8430907 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.4536. Min Act: -0.1700
Data Index: 1932829 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.4536. Min Act: -0.1700
Data Index: 312508 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.4536. Min Act: -0.1700
Data Index: 5135198 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.4223. Min Act: -0.1700
Data Index: 2444506 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.4536. Min Act: -0.1700
Data Index: 7884656 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.4536. Min Act: -0.1700
Data Index: 4650998 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.4536. Min Act: -0.1700
Data Index: 6495497 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19