Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4918 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.7006. Min Act: -0.1700
Data Index: 1793559 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.6069. Min Act: -0.1700
Data Index: 6902563 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.5756. Min Act: -0.1700
Data Index: 2597717 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.5444. Min Act: -0.1700
Data Index: 3970464 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.5444. Min Act: -0.1700
Data Index: 7793853 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.5131. Min Act: -0.1700
Data Index: 6645209 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.4819. Min Act: -0.1700
Data Index: 554869 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.4819. Min Act: -0.1700
Data Index: 699424 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.4819. Min Act: -0.1700
Data Index: 7549259 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.4506. Min Act: -0.1700
Data Index: 3919326 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.4194. Min Act: -0.1700
Data Index: 424393 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.4194. Min Act: -0.1700
Data Index: 1056765 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.4194. Min Act: -0.1700
Data Index: 5773794 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.3881. Min Act: -0.1700
Data Index: 6420042 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.3881. Min Act: -0.1700
Data Index: 6008373 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.3881. Min Act: -0.1700
Data Index: 8827887 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.3881. Min Act: -0.1700
Data Index: 7525418 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.3569. Min Act: -0.1700
Data Index: 3967376 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.3881. Min Act: -0.1700
Data Index: 1822677 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7006. Min Range: -5.7006
Max Act: 5.3881. Min Act: -0.1700
Data Index: 6488362 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19