Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.9216. Min Act: -0.1700
Data Index: 2120375 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7966. Min Act: -0.1700
Data Index: 835002 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.8591. Min Act: -0.1700
Data Index: 4130836 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.8279. Min Act: -0.1700
Data Index: 8726864 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7966. Min Act: -0.1700
Data Index: 7420960 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7654. Min Act: -0.1700
Data Index: 3486178 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.8279. Min Act: -0.1700
Data Index: 4509428 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7654. Min Act: -0.1700
Data Index: 7139608 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7654. Min Act: -0.1700
Data Index: 1490496 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7654. Min Act: -0.1700
Data Index: 1623150 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7341. Min Act: -0.1700
Data Index: 2008523 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7654. Min Act: -0.1700
Data Index: 5781490 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7029. Min Act: -0.1700
Data Index: 2020885 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7341. Min Act: -0.1700
Data Index: 1221333 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7029. Min Act: -0.1700
Data Index: 8280049 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7029. Min Act: -0.1700
Data Index: 1302506 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7029. Min Act: -0.1700
Data Index: 4452613 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7029. Min Act: -0.1700
Data Index: 2361368 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.7341. Min Act: -0.1700
Data Index: 3897649 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9216. Min Range: -5.9216
Max Act: 5.6716. Min Act: -0.1700
Data Index: 3650501 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19