Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4066 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3612. Min Range: -9.3612
Max Act: 9.3612. Min Act: -0.1700
Data Index: 3167267 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3612. Min Range: -9.3612
Max Act: 9.3612. Min Act: -0.1700
Data Index: 4658063 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3612. Min Range: -9.3612
Max Act: 9.0487. Min Act: -0.1700
Data Index: 2208796 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.9862. Min Act: -0.1700
Data Index: 4242060 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.9862. Min Act: -0.1700
Data Index: 3956063 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.8612. Min Act: -0.1700
Data Index: 6725476 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.9862. Min Act: -0.1700
Data Index: 1257601 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.9237. Min Act: -0.1700
Data Index: 6112496 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.7987. Min Act: -0.1700
Data Index: 2544930 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.7987. Min Act: -0.1700
Data Index: 2943747 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.6737. Min Act: -0.1700
Data Index: 4112451 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.6737. Min Act: -0.1700
Data Index: 6554062 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.6112. Min Act: -0.1700
Data Index: 6591326 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.6737. Min Act: -0.1700
Data Index: 7573024 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.5487. Min Act: -0.1700
Data Index: 5975286 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.4862. Min Act: -0.1700
Data Index: 220464 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.4862. Min Act: -0.1700
Data Index: 1429932 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.5487. Min Act: -0.1700
Data Index: 3706574 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.4862. Min Act: -0.1700
Data Index: 3675463 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3612. Min Range: -9.3612
Max Act: 8.5487. Min Act: -0.1700
Data Index: 3921756 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19