Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.3205. Min Act: -0.1700
Data Index: 4946967 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.2893. Min Act: -0.1700
Data Index: 8820798 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.0705. Min Act: -0.1700
Data Index: 2992135 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3205. Min Range: -4.3205
Max Act: 4.0392. Min Act: -0.1700
Data Index: 8661415 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.9454. Min Act: -0.1700
Data Index: 2992132 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.9142. Min Act: -0.1700
Data Index: 3890386 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.8829. Min Act: -0.1700
Data Index: 1570760 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.8516. Min Act: -0.1700
Data Index: 423582 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.8516. Min Act: -0.1700
Data Index: 7227921 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.8204. Min Act: -0.1700
Data Index: 6137069 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.8360. Min Act: -0.1700
Data Index: 8540330 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.8360. Min Act: -0.1700
Data Index: 5817782 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.8204. Min Act: -0.1700
Data Index: 8803806 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.8204. Min Act: -0.1700
Data Index: 3374548 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.8047. Min Act: -0.1700
Data Index: 2997990 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.8047. Min Act: -0.1700
Data Index: 6137070 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.8204. Min Act: -0.1700
Data Index: 8360671 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.7891. Min Act: -0.1700
Data Index: 2997989 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.7735. Min Act: -0.1700
Data Index: 8456611 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3205. Min Range: -4.3205
Max Act: 3.7735. Min Act: -0.1700
Data Index: 358920 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19