Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.7520. Min Act: -0.1700
Data Index: 960658 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.5957. Min Act: -0.1700
Data Index: 960661 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.4707. Min Act: -0.1700
Data Index: 8157783 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.3457. Min Act: -0.1700
Data Index: 4600139 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.2832. Min Act: -0.1700
Data Index: 7752907 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.2832. Min Act: -0.1700
Data Index: 4597845 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.2207. Min Act: -0.1700
Data Index: 1058806 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.1895. Min Act: -0.1700
Data Index: 4389019 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.1270. Min Act: -0.1700
Data Index: 4638733 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.1582. Min Act: -0.1700
Data Index: 1821000 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.1270. Min Act: -0.1700
Data Index: 1114441 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.1270. Min Act: -0.1700
Data Index: 6129229 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.1270. Min Act: -0.1700
Data Index: 1450859 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.0957. Min Act: -0.1700
Data Index: 5121596 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.0957. Min Act: -0.1700
Data Index: 6684993 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.0645. Min Act: -0.1700
Data Index: 1232513 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.0645. Min Act: -0.1700
Data Index: 6675608 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.0332. Min Act: -0.1700
Data Index: 3448542 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.0332. Min Act: -0.1700
Data Index: 4784098 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7520. Min Range: -5.7520
Max Act: 5.0332. Min Act: -0.1700
Data Index: 6486764 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19