Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 326 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.9429. Min Act: -0.1700
Data Index: 1380183 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8576. Min Act: -0.1700
Data Index: 5158900 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8576. Min Act: -0.1700
Data Index: 4427023 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8576. Min Act: -0.1700
Data Index: 4202960 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8405. Min Act: -0.1700
Data Index: 2956090 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8576. Min Act: -0.1700
Data Index: 5550817 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8576. Min Act: -0.1700
Data Index: 1969680 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8576. Min Act: -0.1700
Data Index: 654273 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8405. Min Act: -0.1700
Data Index: 2551900 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8405. Min Act: -0.1700
Data Index: 2374790 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8405. Min Act: -0.1700
Data Index: 6385345 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8234. Min Act: -0.1700
Data Index: 8296670 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8405. Min Act: -0.1700
Data Index: 6208123 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8405. Min Act: -0.1700
Data Index: 4669011 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8405. Min Act: -0.1700
Data Index: 5879618 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8062. Min Act: -0.1700
Data Index: 4280148 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8234. Min Act: -0.1700
Data Index: 5400420 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8062. Min Act: -0.1700
Data Index: 1130457 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8062. Min Act: -0.1700
Data Index: 5701428 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9429. Min Range: -1.9429
Max Act: 1.8234. Min Act: -0.1700
Data Index: 7800660 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19