Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1453 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0803. Min Range: -8.0803
Max Act: 8.0803. Min Act: -0.1700
Data Index: 7373013 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.7991. Min Act: -0.1700
Data Index: 2686313 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.7678. Min Act: -0.1700
Data Index: 6030613 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.7053. Min Act: -0.1700
Data Index: 1281242 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.7053. Min Act: -0.1700
Data Index: 4955586 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.5491. Min Act: -0.1700
Data Index: 3276824 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.5491. Min Act: -0.1700
Data Index: 8011316 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.4866. Min Act: -0.1700
Data Index: 1271513 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.4553. Min Act: -0.1700
Data Index: 2213455 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.4866. Min Act: -0.1700
Data Index: 7268440 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.3928. Min Act: -0.1700
Data Index: 374799 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.4553. Min Act: -0.1700
Data Index: 7702409 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.3928. Min Act: -0.1700
Data Index: 3749488 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.2991. Min Act: -0.1700
Data Index: 1311566 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.2991. Min Act: -0.1700
Data Index: 928617 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.2678. Min Act: -0.1699
Data Index: 5968358 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.3616. Min Act: -0.1700
Data Index: 76594 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.2678. Min Act: -0.1700
Data Index: 5244072 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.2991. Min Act: -0.1700
Data Index: 1061697 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0803. Min Range: -8.0803
Max Act: 7.2991. Min Act: -0.1700
Data Index: 4141875 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19