Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1926 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1990. Min Range: -5.1990
Max Act: 5.1990. Min Act: -0.1700
Data Index: 5204273 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1990. Min Range: -5.1990
Max Act: 5.1053. Min Act: -0.1700
Data Index: 2925682 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1990. Min Range: -5.1990
Max Act: 5.1053. Min Act: -0.1700
Data Index: 4365629 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1990. Min Range: -5.1990
Max Act: 5.0740. Min Act: -0.1700
Data Index: 2925642 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1990. Min Range: -5.1990
Max Act: 5.0740. Min Act: -0.1700
Data Index: 4365622 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1990. Min Range: -5.1990
Max Act: 5.0428. Min Act: -0.1700
Data Index: 8339512 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1990. Min Range: -5.1990
Max Act: 5.0428. Min Act: -0.1700
Data Index: 4365632 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1990. Min Range: -5.1990
Max Act: 5.0428. Min Act: -0.1700
Data Index: 7483182 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1990. Min Range: -5.1990
Max Act: 4.9803. Min Act: -0.1700
Data Index: 380745 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1990. Min Range: -5.1990
Max Act: 4.9490. Min Act: -0.1700
Data Index: 2925671 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1990. Min Range: -5.1990
Max Act: 4.9490. Min Act: -0.1700
Data Index: 8057964 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1990. Min Range: -5.1990
Max Act: 4.9490. Min Act: -0.1700
Data Index: 7483181 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1990. Min Range: -5.1990
Max Act: 4.9178. Min Act: -0.1700
Data Index: 4365618 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1990. Min Range: -5.1990
Max Act: 4.9490. Min Act: -0.1700
Data Index: 4264150 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1990. Min Range: -5.1990
Max Act: 4.9178. Min Act: -0.1700
Data Index: 718969 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1990. Min Range: -5.1990
Max Act: 4.8865. Min Act: -0.1700
Data Index: 2925627 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1990. Min Range: -5.1990
Max Act: 4.8865. Min Act: -0.1700
Data Index: 2925689 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1990. Min Range: -5.1990
Max Act: 4.8865. Min Act: -0.1700
Data Index: 8167599 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1990. Min Range: -5.1990
Max Act: 4.8865. Min Act: -0.1700
Data Index: 1584521 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1990. Min Range: -5.1990
Max Act: 4.8553. Min Act: -0.1700
Data Index: 3198228 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19