Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3330 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.1557. Min Act: -0.1700
Data Index: 87653 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.1869. Min Act: -0.1700
Data Index: 6679534 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.1244. Min Act: -0.1700
Data Index: 8299318 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.1244. Min Act: -0.1700
Data Index: 6248758 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0932. Min Act: -0.1700
Data Index: 6854122 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0932. Min Act: -0.1700
Data Index: 4849523 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0619. Min Act: -0.1700
Data Index: 2515781 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0619. Min Act: -0.1700
Data Index: 3602153 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0619. Min Act: -0.1700
Data Index: 878259 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0619. Min Act: -0.1700
Data Index: 249048 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0307. Min Act: -0.1700
Data Index: 5038675 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0307. Min Act: -0.1700
Data Index: 6839358 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0307. Min Act: -0.1700
Data Index: 5352089 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0307. Min Act: -0.1700
Data Index: 5018904 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9994. Min Act: -0.1700
Data Index: 2129989 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9994. Min Act: -0.1700
Data Index: 2478965 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9994. Min Act: -0.1700
Data Index: 2486480 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9994. Min Act: -0.1700
Data Index: 2184469 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0307. Min Act: -0.1700
Data Index: 5566674 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9994. Min Act: -0.1700
Data Index: 1811438 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19