Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3404. Min Range: -4.3404
Max Act: 4.3404. Min Act: -0.1700
Data Index: 4460238 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3404. Min Range: -4.3404
Max Act: 4.2779. Min Act: -0.1700
Data Index: 4460239 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3404. Min Range: -4.3404
Max Act: 4.2466. Min Act: -0.1700
Data Index: 4460235 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3404. Min Range: -4.3404
Max Act: 4.1216. Min Act: -0.1700
Data Index: 6028189 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.9340. Min Act: -0.1700
Data Index: 6428464 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.9028. Min Act: -0.1700
Data Index: 2046206 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.9028. Min Act: -0.1700
Data Index: 5028836 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.8715. Min Act: -0.1700
Data Index: 2758340 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.9028. Min Act: -0.1700
Data Index: 4502103 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.8090. Min Act: -0.1700
Data Index: 5367122 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.8090. Min Act: -0.1700
Data Index: 535486 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.7777. Min Act: -0.1700
Data Index: 6117805 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.8090. Min Act: -0.1700
Data Index: 2635818 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.8090. Min Act: -0.1700
Data Index: 7831104 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.7777. Min Act: -0.1700
Data Index: 5658467 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.8090. Min Act: -0.1700
Data Index: 5511232 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.7777. Min Act: -0.1700
Data Index: 641424 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.7621. Min Act: -0.1700
Data Index: 3157538 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.7621. Min Act: -0.1700
Data Index: 419678 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3404. Min Range: -4.3404
Max Act: 3.8090. Min Act: -0.1700
Data Index: 641423 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19