Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3165 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.4965. Min Act: -0.1700
Data Index: 566026 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.4653. Min Act: -0.1700
Data Index: 2300013 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.4340. Min Act: -0.1700
Data Index: 2001988 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.3715. Min Act: -0.1700
Data Index: 1515339 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.3403. Min Act: -0.1700
Data Index: 468805 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.3090. Min Act: -0.1700
Data Index: 2575500 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.3090. Min Act: -0.1700
Data Index: 7509675 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.3090. Min Act: -0.1700
Data Index: 2906960 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.3090. Min Act: -0.1700
Data Index: 1459386 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.3090. Min Act: -0.1700
Data Index: 5616735 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.2778. Min Act: -0.1700
Data Index: 4175743 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.3090. Min Act: -0.1700
Data Index: 1781314 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.2778. Min Act: -0.1700
Data Index: 4951200 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.2778. Min Act: -0.1700
Data Index: 868186 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.2465. Min Act: -0.1700
Data Index: 3806306 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.2778. Min Act: -0.1700
Data Index: 6315719 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.2465. Min Act: -0.1700
Data Index: 2600149 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.2465. Min Act: -0.1700
Data Index: 4292753 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.2465. Min Act: -0.1700
Data Index: 474487 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4965. Min Range: -5.4965
Max Act: 5.2465. Min Act: -0.1700
Data Index: 5418434 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19