Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1922 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.6764. Min Act: -0.1700
Data Index: 8638144 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.5355. Min Act: -0.1700
Data Index: 4750367 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.5355. Min Act: -0.1700
Data Index: 6060632 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.5199. Min Act: -0.1700
Data Index: 2104232 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.4729. Min Act: -0.1700
Data Index: 5742555 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.4729. Min Act: -0.1700
Data Index: 6060633 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.4572. Min Act: -0.1700
Data Index: 1439165 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.4572. Min Act: -0.1700
Data Index: 5061148 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.3945. Min Act: -0.1700
Data Index: 3037919 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.4102. Min Act: -0.1700
Data Index: 1551724 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.4259. Min Act: -0.1700
Data Index: 2030311 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.4102. Min Act: -0.1700
Data Index: 8157872 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.3945. Min Act: -0.1700
Data Index: 4721516 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.3788. Min Act: -0.1700
Data Index: 5188385 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.3788. Min Act: -0.1700
Data Index: 4769318 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.3632. Min Act: -0.1700
Data Index: 2029276 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.3632. Min Act: -0.1700
Data Index: 8187201 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.3788. Min Act: -0.1700
Data Index: 3233985 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.3788. Min Act: -0.1700
Data Index: 420847 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6764. Min Range: -3.6764
Max Act: 3.3632. Min Act: -0.1700
Data Index: 7989642 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19