Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3325 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2023. Min Range: -6.2023
Max Act: 6.2023. Min Act: -0.1700
Data Index: 3557964 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2023. Min Range: -6.2023
Max Act: 6.1710. Min Act: -0.1700
Data Index: 1644537 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2023. Min Range: -6.2023
Max Act: 6.1398. Min Act: -0.1700
Data Index: 5181998 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2023. Min Range: -6.2023
Max Act: 6.1085. Min Act: -0.1700
Data Index: 300591 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2023. Min Range: -6.2023
Max Act: 6.0460. Min Act: -0.1700
Data Index: 553522 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2023. Min Range: -6.2023
Max Act: 6.1085. Min Act: -0.1700
Data Index: 287656 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2023. Min Range: -6.2023
Max Act: 6.0148. Min Act: -0.1700
Data Index: 4649723 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2023. Min Range: -6.2023
Max Act: 6.0148. Min Act: -0.1700
Data Index: 2249231 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2023. Min Range: -6.2023
Max Act: 6.0148. Min Act: -0.1700
Data Index: 5605161 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2023. Min Range: -6.2023
Max Act: 5.9523. Min Act: -0.1700
Data Index: 4267652 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2023. Min Range: -6.2023
Max Act: 5.9835. Min Act: -0.1700
Data Index: 3885437 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2023. Min Range: -6.2023
Max Act: 5.9523. Min Act: -0.1700
Data Index: 2920542 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2023. Min Range: -6.2023
Max Act: 5.9210. Min Act: -0.1700
Data Index: 6552937 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2023. Min Range: -6.2023
Max Act: 5.9210. Min Act: -0.1700
Data Index: 5065965 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2023. Min Range: -6.2023
Max Act: 5.9210. Min Act: -0.1700
Data Index: 1781615 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2023. Min Range: -6.2023
Max Act: 5.8898. Min Act: -0.1700
Data Index: 6479256 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2023. Min Range: -6.2023
Max Act: 5.8585. Min Act: -0.1700
Data Index: 500890 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2023. Min Range: -6.2023
Max Act: 5.7960. Min Act: -0.1700
Data Index: 7560517 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2023. Min Range: -6.2023
Max Act: 5.8273. Min Act: -0.1700
Data Index: 3191432 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2023. Min Range: -6.2023
Max Act: 5.7960. Min Act: -0.1700
Data Index: 6294799 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19