Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2852 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.2809. Min Act: -0.1700
Data Index: 3652193 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.1551. Min Act: -0.1700
Data Index: 6095443 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.1079. Min Act: -0.1700
Data Index: 5598714 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0763. Min Act: -0.1700
Data Index: 8131508 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0606. Min Act: -0.1700
Data Index: 2699447 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0606. Min Act: -0.1700
Data Index: 8796956 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0606. Min Act: -0.1700
Data Index: 8726810 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0448. Min Act: -0.1700
Data Index: 4959545 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0290. Min Act: -0.1700
Data Index: 8131506 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0448. Min Act: -0.1700
Data Index: 8233605 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0290. Min Act: -0.1700
Data Index: 5628620 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0290. Min Act: -0.1700
Data Index: 3257864 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0290. Min Act: -0.1700
Data Index: 93623 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0290. Min Act: -0.1700
Data Index: 921446 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0132. Min Act: -0.1700
Data Index: 5938901 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0132. Min Act: -0.1700
Data Index: 5938898 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0132. Min Act: -0.1700
Data Index: 2564439 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0132. Min Act: -0.1700
Data Index: 6164725 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0132. Min Act: -0.1700
Data Index: 6578616 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0132. Min Act: -0.1700
Data Index: 4158099 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19