Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1101. Min Range: -4.1101
Max Act: 4.1101. Min Act: -0.1700
Data Index: 4029769 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1101. Min Range: -4.1101
Max Act: 4.0789. Min Act: -0.1700
Data Index: 6346783 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1101. Min Range: -4.1101
Max Act: 4.0476. Min Act: -0.1700
Data Index: 8173526 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.8444. Min Act: -0.1700
Data Index: 1231391 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.7662. Min Act: -0.1700
Data Index: 8816968 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.7193. Min Act: -0.1700
Data Index: 7560115 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.6567. Min Act: -0.1700
Data Index: 6830210 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.6724. Min Act: -0.1700
Data Index: 605162 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.6724. Min Act: -0.1700
Data Index: 1713177 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.6567. Min Act: -0.1700
Data Index: 4868084 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.6411. Min Act: -0.1700
Data Index: 5708931 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.6411. Min Act: -0.1700
Data Index: 3339324 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.6254. Min Act: -0.1700
Data Index: 6159901 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.6411. Min Act: -0.1700
Data Index: 237502 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.6098. Min Act: -0.1700
Data Index: 69204 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.6098. Min Act: -0.1700
Data Index: 1212399 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.6098. Min Act: -0.1700
Data Index: 5281910 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.5941. Min Act: -0.1700
Data Index: 954628 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.6098. Min Act: -0.1700
Data Index: 4297810 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1101. Min Range: -4.1101
Max Act: 3.5785. Min Act: -0.1700
Data Index: 5295070 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19