Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1741 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.6098. Min Act: -0.1700
Data Index: 4817750 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.5473. Min Act: -0.1700
Data Index: 1476481 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.3598. Min Act: -0.1700
Data Index: 8419807 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.2973. Min Act: -0.1700
Data Index: 2353883 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.2973. Min Act: -0.1700
Data Index: 6213666 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.2973. Min Act: -0.1700
Data Index: 8591232 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.2660. Min Act: -0.1700
Data Index: 2679920 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.2660. Min Act: -0.1700
Data Index: 4467468 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.2660. Min Act: -0.1700
Data Index: 7745249 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.2660. Min Act: -0.1700
Data Index: 4062010 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.2660. Min Act: -0.1700
Data Index: 995058 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.2035. Min Act: -0.1700
Data Index: 1446709 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.2035. Min Act: -0.1700
Data Index: 5807548 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.1722. Min Act: -0.1700
Data Index: 5760275 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.2035. Min Act: -0.1700
Data Index: 10199 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.2348. Min Act: -0.1700
Data Index: 8588232 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.2035. Min Act: -0.1700
Data Index: 1527334 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.1722. Min Act: -0.1700
Data Index: 5247178 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.1722. Min Act: -0.1700
Data Index: 8154211 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6098. Min Range: -4.6098
Max Act: 4.1410. Min Act: -0.1700
Data Index: 5190217 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19