Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.2683. Min Act: -0.1700
Data Index: 6158485 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.2370. Min Act: -0.1700
Data Index: 500611 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.2058. Min Act: -0.1700
Data Index: 2004322 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.2058. Min Act: -0.1700
Data Index: 2752692 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.2058. Min Act: -0.1700
Data Index: 1359599 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1432. Min Act: -0.1700
Data Index: 4597553 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1745. Min Act: -0.1700
Data Index: 2229949 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1432. Min Act: -0.1700
Data Index: 1777898 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1432. Min Act: -0.1700
Data Index: 2572845 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1432. Min Act: -0.1700
Data Index: 4278107 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1432. Min Act: -0.1700
Data Index: 4204352 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1432. Min Act: -0.1700
Data Index: 2298820 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1120. Min Act: -0.1700
Data Index: 4179653 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1432. Min Act: -0.1700
Data Index: 5134387 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1120. Min Act: -0.1700
Data Index: 985455 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1120. Min Act: -0.1700
Data Index: 6353070 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1120. Min Act: -0.1700
Data Index: 8431246 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.0807. Min Act: -0.1700
Data Index: 5663002 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1120. Min Act: -0.1700
Data Index: 3400055 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2683. Min Range: -4.2683
Max Act: 4.1120. Min Act: -0.1700
Data Index: 5115372 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19