Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2850 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2804. Min Range: -7.2804
Max Act: 7.2804. Min Act: -0.1700
Data Index: 7360561 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2804. Min Range: -7.2804
Max Act: 7.0304. Min Act: -0.1700
Data Index: 2341313 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.9679. Min Act: -0.1700
Data Index: 298372 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.9367. Min Act: -0.1700
Data Index: 4034317 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.9054. Min Act: -0.1700
Data Index: 6107316 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.8742. Min Act: -0.1700
Data Index: 3215442 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.8429. Min Act: -0.1700
Data Index: 4249246 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.8117. Min Act: -0.1700
Data Index: 6112876 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.8117. Min Act: -0.1700
Data Index: 7478906 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.8117. Min Act: -0.1700
Data Index: 7370983 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.7804. Min Act: -0.1700
Data Index: 1946630 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.8117. Min Act: -0.1700
Data Index: 2954251 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.7492. Min Act: -0.1700
Data Index: 5498328 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.7492. Min Act: -0.1700
Data Index: 829370 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.7179. Min Act: -0.1700
Data Index: 8040842 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.7179. Min Act: -0.1700
Data Index: 298080 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.7179. Min Act: -0.1700
Data Index: 5427996 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.7179. Min Act: -0.1700
Data Index: 1872478 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.6554. Min Act: -0.1700
Data Index: 8658617 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2804. Min Range: -7.2804
Max Act: 6.6554. Min Act: -0.1700
Data Index: 1170138 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19