Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1503 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.4221. Min Act: -0.1700
Data Index: 4384009 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.3909. Min Act: -0.1700
Data Index: 2808428 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.3284. Min Act: -0.1700
Data Index: 303012 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.3596. Min Act: -0.1700
Data Index: 2946087 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.3284. Min Act: -0.1700
Data Index: 7431482 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.3284. Min Act: -0.1700
Data Index: 5701250 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.2971. Min Act: -0.1700
Data Index: 6575508 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.2659. Min Act: -0.1700
Data Index: 339571 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.1721. Min Act: -0.1700
Data Index: 298986 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.1721. Min Act: -0.1700
Data Index: 6348636 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.1721. Min Act: -0.1700
Data Index: 4112751 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.1409. Min Act: -0.1700
Data Index: 72303 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.1409. Min Act: -0.1700
Data Index: 6509050 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.1721. Min Act: -0.1700
Data Index: 3294446 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.0784. Min Act: -0.1700
Data Index: 4198128 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.1096. Min Act: -0.1700
Data Index: 886983 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.0784. Min Act: -0.1700
Data Index: 6146027 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.0784. Min Act: -0.1700
Data Index: 2488828 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.0784. Min Act: -0.1700
Data Index: 7056457 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4221. Min Range: -6.4221
Max Act: 6.0784. Min Act: -0.1700
Data Index: 4673377 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19