Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0601. Min Range: -5.0601
Max Act: 5.0601. Min Act: -0.1700
Data Index: 6192154 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0601. Min Range: -5.0601
Max Act: 5.0289. Min Act: -0.1700
Data Index: 6750748 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.9351. Min Act: -0.1700
Data Index: 4851046 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8726. Min Act: -0.1700
Data Index: 5759460 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.9039. Min Act: -0.1700
Data Index: 214647 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8414. Min Act: -0.1700
Data Index: 8646977 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8414. Min Act: -0.1700
Data Index: 2867780 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8726. Min Act: -0.1700
Data Index: 4463045 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8414. Min Act: -0.1700
Data Index: 3271272 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8414. Min Act: -0.1700
Data Index: 7504712 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8101. Min Act: -0.1700
Data Index: 175633 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8101. Min Act: -0.1700
Data Index: 1301256 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8101. Min Act: -0.1700
Data Index: 6845727 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8101. Min Act: -0.1700
Data Index: 4246564 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8101. Min Act: -0.1700
Data Index: 5088322 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8101. Min Act: -0.1700
Data Index: 2353470 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8101. Min Act: -0.1700
Data Index: 4795107 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.7789. Min Act: -0.1700
Data Index: 787689 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.7789. Min Act: -0.1700
Data Index: 576673 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0601. Min Range: -5.0601
Max Act: 4.8101. Min Act: -0.1700
Data Index: 3801021 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19