Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1403 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.6181. Min Act: -0.1700
Data Index: 8475261 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.4306. Min Act: -0.1700
Data Index: 1452840 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.3681. Min Act: -0.1700
Data Index: 4667814 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.3681. Min Act: -0.1700
Data Index: 6149332 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.3368. Min Act: -0.1700
Data Index: 766390 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.2743. Min Act: -0.1700
Data Index: 851021 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.2431. Min Act: -0.1700
Data Index: 4691756 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.1806. Min Act: -0.1700
Data Index: 439704 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.1493. Min Act: -0.1700
Data Index: 200578 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.1493. Min Act: -0.1700
Data Index: 1084950 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.1181. Min Act: -0.1700
Data Index: 6583234 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.0868. Min Act: -0.1700
Data Index: 7262468 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.0868. Min Act: -0.1700
Data Index: 1694118 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.0556. Min Act: -0.1700
Data Index: 1651900 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.0556. Min Act: -0.1700
Data Index: 4560510 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.0556. Min Act: -0.1700
Data Index: 5937214 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6181. Min Range: -7.6181
Max Act: 6.9931. Min Act: -0.1700
Data Index: 4742007 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6181. Min Range: -7.6181
Max Act: 7.0243. Min Act: -0.1700
Data Index: 567670 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6181. Min Range: -7.6181
Max Act: 6.9931. Min Act: -0.1700
Data Index: 1062035 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6181. Min Range: -7.6181
Max Act: 6.9931. Min Act: -0.1700
Data Index: 6823639 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19