Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1525 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1011. Min Range: -3.1011
Max Act: 3.1011. Min Act: -0.1700
Data Index: 6708566 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1011. Min Range: -3.1011
Max Act: 3.0537. Min Act: -0.1700
Data Index: 1914566 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1011. Min Range: -3.1011
Max Act: 3.0064. Min Act: -0.1700
Data Index: 1040600 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.9906. Min Act: -0.1700
Data Index: 5101200 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.9589. Min Act: -0.1700
Data Index: 881197 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.9114. Min Act: -0.1700
Data Index: 5041423 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.8638. Min Act: -0.1700
Data Index: 2939207 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.8479. Min Act: -0.1700
Data Index: 1075196 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.8479. Min Act: -0.1700
Data Index: 1132497 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.8320. Min Act: -0.1700
Data Index: 2554043 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.8161. Min Act: -0.1700
Data Index: 7095632 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.7843. Min Act: -0.1700
Data Index: 8744970 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.7683. Min Act: -0.1700
Data Index: 4361940 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.7843. Min Act: -0.1700
Data Index: 3012428 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.7524. Min Act: -0.1700
Data Index: 1105002 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.7843. Min Act: -0.1700
Data Index: 4913058 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.7683. Min Act: -0.1700
Data Index: 6118017 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.8161. Min Act: -0.1700
Data Index: 3292254 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.7364. Min Act: -0.1700
Data Index: 5898564 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1011. Min Range: -3.1011
Max Act: 2.7524. Min Act: -0.1700
Data Index: 33290 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19