Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2658 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.7383. Min Act: -0.1700
Data Index: 7229073 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.7695. Min Act: -0.1700
Data Index: 369149 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.7383. Min Act: -0.1700
Data Index: 8121672 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.6758. Min Act: -0.1700
Data Index: 3732258 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.7070. Min Act: -0.1700
Data Index: 5789149 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.7070. Min Act: -0.1700
Data Index: 7038104 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.6758. Min Act: -0.1700
Data Index: 5826582 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.6758. Min Act: -0.1700
Data Index: 4958573 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.6445. Min Act: -0.1700
Data Index: 8244144 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.6445. Min Act: -0.1700
Data Index: 2492899 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.6445. Min Act: -0.1700
Data Index: 8707128 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.6445. Min Act: -0.1700
Data Index: 6633356 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.6133. Min Act: -0.1700
Data Index: 6643848 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.6133. Min Act: -0.1700
Data Index: 7202999 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.5820. Min Act: -0.1700
Data Index: 4088602 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.5820. Min Act: -0.1700
Data Index: 8007598 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.6133. Min Act: -0.1700
Data Index: 5210156 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.6133. Min Act: -0.1700
Data Index: 5881380 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.5820. Min Act: -0.1700
Data Index: 7056147 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7695. Min Range: -4.7695
Max Act: 4.5508. Min Act: -0.1700
Data Index: 2279698 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19