Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5190 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8367. Min Range: -7.8367
Max Act: 7.8367. Min Act: -0.1700
Data Index: 5019719 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8367. Min Range: -7.8367
Max Act: 7.5867. Min Act: -0.1700
Data Index: 8707947 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8367. Min Range: -7.8367
Max Act: 7.3679. Min Act: -0.1700
Data Index: 3781761 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8367. Min Range: -7.8367
Max Act: 7.3054. Min Act: -0.1700
Data Index: 1984862 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8367. Min Range: -7.8367
Max Act: 7.1492. Min Act: -0.1700
Data Index: 7959629 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8367. Min Range: -7.8367
Max Act: 7.1179. Min Act: -0.1700
Data Index: 5279180 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8367. Min Range: -7.8367
Max Act: 7.1492. Min Act: -0.1700
Data Index: 684207 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8367. Min Range: -7.8367
Max Act: 7.0867. Min Act: -0.1700
Data Index: 6267920 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8367. Min Range: -7.8367
Max Act: 7.0867. Min Act: -0.1700
Data Index: 4696551 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8367. Min Range: -7.8367
Max Act: 7.0867. Min Act: -0.1700
Data Index: 2621815 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8367. Min Range: -7.8367
Max Act: 7.0554. Min Act: -0.1700
Data Index: 1130130 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8367. Min Range: -7.8367
Max Act: 7.0554. Min Act: -0.1700
Data Index: 5185876 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8367. Min Range: -7.8367
Max Act: 7.0554. Min Act: -0.1700
Data Index: 8398952 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8367. Min Range: -7.8367
Max Act: 6.9929. Min Act: -0.1700
Data Index: 1224175 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8367. Min Range: -7.8367
Max Act: 6.9929. Min Act: -0.1700
Data Index: 6458217 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8367. Min Range: -7.8367
Max Act: 6.9617. Min Act: -0.1700
Data Index: 4074230 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8367. Min Range: -7.8367
Max Act: 6.9617. Min Act: -0.1700
Data Index: 7488128 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8367. Min Range: -7.8367
Max Act: 6.9304. Min Act: -0.1700
Data Index: 5328436 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8367. Min Range: -7.8367
Max Act: 6.9304. Min Act: -0.1700
Data Index: 8233950 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8367. Min Range: -7.8367
Max Act: 6.8992. Min Act: -0.1700
Data Index: 853502 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19