Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 503 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.8794. Min Act: -0.1700
Data Index: 6535706 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.8794. Min Act: -0.1700
Data Index: 7869549 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.6919. Min Act: -0.1700
Data Index: 5475684 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.7232. Min Act: -0.1700
Data Index: 6667333 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.6919. Min Act: -0.1700
Data Index: 6943077 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.6919. Min Act: -0.1700
Data Index: 3736820 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.6919. Min Act: -0.1700
Data Index: 8418729 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.5982. Min Act: -0.1700
Data Index: 88769 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.5669. Min Act: -0.1700
Data Index: 6781934 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.6294. Min Act: -0.1700
Data Index: 1480106 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.5669. Min Act: -0.1700
Data Index: 6535707 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.5357. Min Act: -0.1700
Data Index: 7973685 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.5357. Min Act: -0.1700
Data Index: 5199473 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.5044. Min Act: -0.1700
Data Index: 4964680 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.5357. Min Act: -0.1700
Data Index: 7437440 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.4419. Min Act: -0.1700
Data Index: 330534 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.4419. Min Act: -0.1700
Data Index: 1551451 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.4732. Min Act: -0.1700
Data Index: 3887318 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.4732. Min Act: -0.1700
Data Index: 8503693 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8794. Min Range: -5.8794
Max Act: 5.4732. Min Act: -0.1700
Data Index: 1474178 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19