Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4268 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3437. Min Range: -7.3437
Max Act: 7.3437. Min Act: -0.1700
Data Index: 168800 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3437. Min Range: -7.3437
Max Act: 7.3437. Min Act: -0.1700
Data Index: 8528393 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3437. Min Range: -7.3437
Max Act: 7.1562. Min Act: -0.1700
Data Index: 7761370 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3437. Min Range: -7.3437
Max Act: 7.1874. Min Act: -0.1700
Data Index: 5338837 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3437. Min Range: -7.3437
Max Act: 7.1562. Min Act: -0.1700
Data Index: 2996398 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3437. Min Range: -7.3437
Max Act: 7.1874. Min Act: -0.1700
Data Index: 2501193 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3437. Min Range: -7.3437
Max Act: 7.0937. Min Act: -0.1700
Data Index: 6281405 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3437. Min Range: -7.3437
Max Act: 7.0624. Min Act: -0.1700
Data Index: 8116690 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3437. Min Range: -7.3437
Max Act: 7.0312. Min Act: -0.1700
Data Index: 7997344 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3437. Min Range: -7.3437
Max Act: 6.9999. Min Act: -0.1700
Data Index: 3400369 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3437. Min Range: -7.3437
Max Act: 6.9687. Min Act: -0.1700
Data Index: 8000857 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3437. Min Range: -7.3437
Max Act: 6.9687. Min Act: -0.1700
Data Index: 5863420 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3437. Min Range: -7.3437
Max Act: 6.9374. Min Act: -0.1700
Data Index: 1831587 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3437. Min Range: -7.3437
Max Act: 6.9062. Min Act: -0.1700
Data Index: 7436827 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3437. Min Range: -7.3437
Max Act: 6.9062. Min Act: -0.1700
Data Index: 5895510 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3437. Min Range: -7.3437
Max Act: 6.9374. Min Act: -0.1700
Data Index: 607364 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3437. Min Range: -7.3437
Max Act: 6.9062. Min Act: -0.1700
Data Index: 547463 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3437. Min Range: -7.3437
Max Act: 6.8749. Min Act: -0.1700
Data Index: 3131272 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3437. Min Range: -7.3437
Max Act: 6.8437. Min Act: -0.1700
Data Index: 2501061 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3437. Min Range: -7.3437
Max Act: 6.8749. Min Act: -0.1700
Data Index: 8192022 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19