Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.2679. Min Act: -0.1700
Data Index: 2757660 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.2679. Min Act: -0.1700
Data Index: 5647161 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.1742. Min Act: -0.1700
Data Index: 6915228 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.1742. Min Act: -0.1700
Data Index: 5533284 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.1429. Min Act: -0.1700
Data Index: 6073683 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.1429. Min Act: -0.1700
Data Index: 812289 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.1117. Min Act: -0.1700
Data Index: 18052 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.1117. Min Act: -0.1700
Data Index: 5850989 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.1117. Min Act: -0.1700
Data Index: 2434040 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.0804. Min Act: -0.1700
Data Index: 1502671 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.0804. Min Act: -0.1700
Data Index: 2337407 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.0492. Min Act: -0.1700
Data Index: 5003633 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.0492. Min Act: -0.1700
Data Index: 3868964 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.0492. Min Act: -0.1700
Data Index: 2723487 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.0492. Min Act: -0.1700
Data Index: 8691071 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.0492. Min Act: -0.1700
Data Index: 7169720 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2679. Min Range: -6.2679
Max Act: 6.0179. Min Act: -0.1700
Data Index: 780451 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2679. Min Range: -6.2679
Max Act: 5.9867. Min Act: -0.1700
Data Index: 5232189 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2679. Min Range: -6.2679
Max Act: 5.9867. Min Act: -0.1700
Data Index: 5729018 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2679. Min Range: -6.2679
Max Act: 5.9867. Min Act: -0.1700
Data Index: 6793348 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19