Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0425. Min Range: -5.0425
Max Act: 5.0425. Min Act: -0.1700
Data Index: 5440902 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.8238. Min Act: -0.1700
Data Index: 5739543 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.8238. Min Act: -0.1700
Data Index: 6161605 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.7613. Min Act: -0.1700
Data Index: 7954929 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.7300. Min Act: -0.1700
Data Index: 7601655 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.6988. Min Act: -0.1700
Data Index: 289153 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.7300. Min Act: -0.1700
Data Index: 6863437 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.7300. Min Act: -0.1700
Data Index: 4632228 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.6363. Min Act: -0.1700
Data Index: 1225930 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.6363. Min Act: -0.1700
Data Index: 3628956 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.6675. Min Act: -0.1700
Data Index: 8037714 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.6675. Min Act: -0.1700
Data Index: 3122534 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.6363. Min Act: -0.1700
Data Index: 1762862 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.6363. Min Act: -0.1700
Data Index: 6396140 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.6363. Min Act: -0.1700
Data Index: 1816234 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.5738. Min Act: -0.1700
Data Index: 7828817 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.6050. Min Act: -0.1700
Data Index: 4587971 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.6050. Min Act: -0.1700
Data Index: 7647372 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.5738. Min Act: -0.1700
Data Index: 4514114 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0425. Min Range: -5.0425
Max Act: 4.6050. Min Act: -0.1700
Data Index: 4441585 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19