Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6360 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0590. Min Range: -8.0590
Max Act: 8.0590. Min Act: -0.1700
Data Index: 2156708 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.8715. Min Act: -0.1700
Data Index: 3697898 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.8403. Min Act: -0.1700
Data Index: 1346974 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.8403. Min Act: -0.1700
Data Index: 8277288 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.7778. Min Act: -0.1700
Data Index: 956453 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.7465. Min Act: -0.1700
Data Index: 2552507 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.6528. Min Act: -0.1700
Data Index: 6747379 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.6528. Min Act: -0.1700
Data Index: 7388265 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.5903. Min Act: -0.1700
Data Index: 3016223 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.5278. Min Act: -0.1700
Data Index: 966403 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.5278. Min Act: -0.1700
Data Index: 910832 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.4965. Min Act: -0.1700
Data Index: 7812134 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.4965. Min Act: -0.1700
Data Index: 2965763 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.4965. Min Act: -0.1700
Data Index: 3759118 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.4340. Min Act: -0.1700
Data Index: 244690 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.3715. Min Act: -0.1700
Data Index: 8668681 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.3715. Min Act: -0.1700
Data Index: 464296 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.4028. Min Act: -0.1700
Data Index: 7321567 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.4028. Min Act: -0.1700
Data Index: 4120983 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.3715. Min Act: -0.1700
Data Index: 8171027 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19