Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1657 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.5750. Min Act: -0.1700
Data Index: 4580815 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.6062. Min Act: -0.1700
Data Index: 505305 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.5750. Min Act: -0.1700
Data Index: 949625 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.5750. Min Act: -0.1700
Data Index: 7946414 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.5437. Min Act: -0.1700
Data Index: 1075114 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.5125. Min Act: -0.1700
Data Index: 2961053 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.4187. Min Act: -0.1700
Data Index: 2174240 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.4187. Min Act: -0.1700
Data Index: 7035076 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.4187. Min Act: -0.1700
Data Index: 6184327 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.3562. Min Act: -0.1700
Data Index: 1478571 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.3562. Min Act: -0.1700
Data Index: 4800268 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.3562. Min Act: -0.1700
Data Index: 8164215 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.3875. Min Act: -0.1700
Data Index: 1781990 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.2937. Min Act: -0.1700
Data Index: 2880555 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.3250. Min Act: -0.1700
Data Index: 1444620 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.3250. Min Act: -0.1700
Data Index: 6458909 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.3250. Min Act: -0.1700
Data Index: 6703577 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.2937. Min Act: -0.1700
Data Index: 5725984 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.2625. Min Act: -0.1700
Data Index: 653545 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6062. Min Range: -6.6062
Max Act: 6.2937. Min Act: -0.1700
Data Index: 3275613 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19