Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6396 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.6150. Min Act: -0.1700
Data Index: 3715252 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.6150. Min Act: -0.1700
Data Index: 1870364 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.5837. Min Act: -0.1700
Data Index: 6188854 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.5525. Min Act: -0.1700
Data Index: 6448838 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.4900. Min Act: -0.1700
Data Index: 280953 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.4587. Min Act: -0.1700
Data Index: 1294633 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.4275. Min Act: -0.1700
Data Index: 3070904 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.3650. Min Act: -0.1700
Data Index: 8137760 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.3650. Min Act: -0.1700
Data Index: 7459079 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.4275. Min Act: -0.1700
Data Index: 2244932 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.3650. Min Act: -0.1700
Data Index: 2928682 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.3650. Min Act: -0.1700
Data Index: 1138717 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.3337. Min Act: -0.1700
Data Index: 1707861 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.3337. Min Act: -0.1700
Data Index: 6083629 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.3650. Min Act: -0.1700
Data Index: 3456444 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.3337. Min Act: -0.1700
Data Index: 679520 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.2712. Min Act: -0.1700
Data Index: 7212319 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.3025. Min Act: -0.1700
Data Index: 5759719 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.3025. Min Act: -0.1700
Data Index: 2601981 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6150. Min Range: -5.6150
Max Act: 5.2712. Min Act: -0.1700
Data Index: 2122627 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19