Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3613 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.4677. Min Act: -0.1700
Data Index: 8480540 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.4677. Min Act: -0.1700
Data Index: 5665647 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.2177. Min Act: -0.1700
Data Index: 585424 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.2177. Min Act: -0.1700
Data Index: 5373559 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.2177. Min Act: -0.1700
Data Index: 2688783 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.2177. Min Act: -0.1700
Data Index: 2021871 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1552. Min Act: -0.1700
Data Index: 585423 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1865. Min Act: -0.1700
Data Index: 4732557 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1865. Min Act: -0.1700
Data Index: 2768875 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1865. Min Act: -0.1700
Data Index: 7760903 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1865. Min Act: -0.1700
Data Index: 1426319 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1865. Min Act: -0.1700
Data Index: 2174949 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1552. Min Act: -0.1700
Data Index: 229355 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1552. Min Act: -0.1700
Data Index: 822445 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1552. Min Act: -0.1700
Data Index: 3496531 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1240. Min Act: -0.1700
Data Index: 4213559 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1240. Min Act: -0.1700
Data Index: 7506924 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1240. Min Act: -0.1700
Data Index: 545295 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1240. Min Act: -0.1700
Data Index: 2046348 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4677. Min Range: -5.4677
Max Act: 5.1240. Min Act: -0.1700
Data Index: 8413802 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19