Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.8336. Min Act: -0.1700
Data Index: 1518203 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.6148. Min Act: -0.1700
Data Index: 338393 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.6148. Min Act: -0.1700
Data Index: 5871743 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.5211. Min Act: -0.1700
Data Index: 5011905 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.5211. Min Act: -0.1700
Data Index: 6572795 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.4898. Min Act: -0.1700
Data Index: 637559 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.3648. Min Act: -0.1700
Data Index: 2716648 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.3336. Min Act: -0.1700
Data Index: 5011583 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.3023. Min Act: -0.1700
Data Index: 2010662 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.3023. Min Act: -0.1700
Data Index: 512115 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.2711. Min Act: -0.1700
Data Index: 1722754 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.2711. Min Act: -0.1700
Data Index: 8200670 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.2398. Min Act: -0.1700
Data Index: 6930823 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.2086. Min Act: -0.1700
Data Index: 8321890 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.2398. Min Act: -0.1700
Data Index: 2452603 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.2398. Min Act: -0.1700
Data Index: 8300726 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.2398. Min Act: -0.1700
Data Index: 3701918 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.1773. Min Act: -0.1700
Data Index: 6866086 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.1461. Min Act: -0.1700
Data Index: 2733597 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8336. Min Range: -5.8336
Max Act: 5.1773. Min Act: -0.1700
Data Index: 7420225 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19