Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3178 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.9651. Min Act: -0.1700
Data Index: 7027735 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.9339. Min Act: -0.1700
Data Index: 2025290 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.9339. Min Act: -0.1700
Data Index: 622713 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.9339. Min Act: -0.1700
Data Index: 7710416 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.9339. Min Act: -0.1700
Data Index: 6417394 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.8401. Min Act: -0.1700
Data Index: 4150578 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.7776. Min Act: -0.1700
Data Index: 6774108 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.8089. Min Act: -0.1700
Data Index: 7591796 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.7776. Min Act: -0.1700
Data Index: 4682817 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.8089. Min Act: -0.1700
Data Index: 6051318 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.7151. Min Act: -0.1700
Data Index: 2611028 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.7464. Min Act: -0.1700
Data Index: 1635292 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.7464. Min Act: -0.1700
Data Index: 7329790 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.7776. Min Act: -0.1700
Data Index: 4081463 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.7776. Min Act: -0.1700
Data Index: 4570867 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.7151. Min Act: -0.1700
Data Index: 5586332 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.6214. Min Act: -0.1700
Data Index: 388772 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.6839. Min Act: -0.1700
Data Index: 3710711 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.6839. Min Act: -0.1700
Data Index: 5294679 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9651. Min Range: -4.9651
Max Act: 4.7151. Min Act: -0.1700
Data Index: 4259640 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19