Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.8547. Min Act: -0.1700
Data Index: 1136977 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.7609. Min Act: -0.1700
Data Index: 4611601 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.7297. Min Act: -0.1700
Data Index: 1914901 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.7297. Min Act: -0.1700
Data Index: 7440829 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.7297. Min Act: -0.1700
Data Index: 2476886 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6984. Min Act: -0.1700
Data Index: 1220187 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6672. Min Act: -0.1700
Data Index: 1220192 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6672. Min Act: -0.1700
Data Index: 1220191 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6359. Min Act: -0.1700
Data Index: 6838977 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6359. Min Act: -0.1700
Data Index: 7778791 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6359. Min Act: -0.1700
Data Index: 6613154 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6359. Min Act: -0.1700
Data Index: 1220188 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6359. Min Act: -0.1700
Data Index: 3754843 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6047. Min Act: -0.1700
Data Index: 6838979 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6047. Min Act: -0.1700
Data Index: 1220186 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6047. Min Act: -0.1700
Data Index: 7707742 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6047. Min Act: -0.1700
Data Index: 6036528 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6047. Min Act: -0.1700
Data Index: 8672060 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6047. Min Act: -0.1700
Data Index: 4381766 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8547. Min Range: -4.8547
Max Act: 4.6047. Min Act: -0.1700
Data Index: 3463811 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19