Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4819 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.6072. Min Act: -0.1700
Data Index: 4857728 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.5759. Min Act: -0.1700
Data Index: 3957860 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.4976. Min Act: -0.1700
Data Index: 4373568 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3879. Min Act: -0.1700
Data Index: 7863090 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3722. Min Act: -0.1700
Data Index: 3963427 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3722. Min Act: -0.1700
Data Index: 1365779 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3565. Min Act: -0.1700
Data Index: 8654028 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3565. Min Act: -0.1700
Data Index: 1943314 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3408. Min Act: -0.1700
Data Index: 8417791 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3251. Min Act: -0.1700
Data Index: 2212663 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3251. Min Act: -0.1700
Data Index: 8116182 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3408. Min Act: -0.1700
Data Index: 7805083 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3251. Min Act: -0.1700
Data Index: 7511736 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3251. Min Act: -0.1700
Data Index: 63860 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3094. Min Act: -0.1700
Data Index: 6892772 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2780. Min Act: -0.1700
Data Index: 321725 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2780. Min Act: -0.1700
Data Index: 3412780 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2780. Min Act: -0.1700
Data Index: 5420078 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2780. Min Act: -0.1700
Data Index: 8775258 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2780. Min Act: -0.1700
Data Index: 56574 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19