Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1379 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.8803. Min Act: -0.1700
Data Index: 1070463 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.8490. Min Act: -0.1700
Data Index: 6837764 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6613. Min Act: -0.1700
Data Index: 5463248 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5987. Min Act: -0.1700
Data Index: 4396865 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6613. Min Act: -0.1700
Data Index: 3867469 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5987. Min Act: -0.1700
Data Index: 831522 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5987. Min Act: -0.1700
Data Index: 1486496 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5987. Min Act: -0.1700
Data Index: 8095951 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5987. Min Act: -0.1700
Data Index: 5438402 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5674. Min Act: -0.1700
Data Index: 7054221 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6300. Min Act: -0.1700
Data Index: 4063446 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5987. Min Act: -0.1700
Data Index: 5530496 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5674. Min Act: -0.1700
Data Index: 2431313 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5674. Min Act: -0.1700
Data Index: 3891681 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5987. Min Act: -0.1700
Data Index: 6748651 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5674. Min Act: -0.1700
Data Index: 537316 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5987. Min Act: -0.1700
Data Index: 2773732 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5361. Min Act: -0.1700
Data Index: 5768429 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5361. Min Act: -0.1700
Data Index: 4942983 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.5205. Min Act: -0.1700
Data Index: 4356179 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19