Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3094 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2730. Min Range: -3.2730
Max Act: 3.2730. Min Act: -0.1700
Data Index: 6033477 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2730. Min Range: -3.2730
Max Act: 3.1315. Min Act: -0.1700
Data Index: 8226846 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2730. Min Range: -3.2730
Max Act: 3.1157. Min Act: -0.1700
Data Index: 5948017 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2730. Min Range: -3.2730
Max Act: 3.0842. Min Act: -0.1700
Data Index: 2234323 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2730. Min Range: -3.2730
Max Act: 3.0527. Min Act: -0.1700
Data Index: 1962578 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2730. Min Range: -3.2730
Max Act: 3.0527. Min Act: -0.1700
Data Index: 7257415 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2730. Min Range: -3.2730
Max Act: 3.0211. Min Act: -0.1700
Data Index: 5609459 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2730. Min Range: -3.2730
Max Act: 3.0053. Min Act: -0.1700
Data Index: 1341172 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2730. Min Range: -3.2730
Max Act: 3.0211. Min Act: -0.1700
Data Index: 7983531 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2730. Min Range: -3.2730
Max Act: 2.9895. Min Act: -0.1700
Data Index: 7221817 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2730. Min Range: -3.2730
Max Act: 2.9737. Min Act: -0.1700
Data Index: 4177480 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2730. Min Range: -3.2730
Max Act: 2.9737. Min Act: -0.1700
Data Index: 8182740 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2730. Min Range: -3.2730
Max Act: 2.9895. Min Act: -0.1700
Data Index: 2590130 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2730. Min Range: -3.2730
Max Act: 2.9737. Min Act: -0.1700
Data Index: 4542575 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2730. Min Range: -3.2730
Max Act: 2.9737. Min Act: -0.1700
Data Index: 7043817 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2730. Min Range: -3.2730
Max Act: 2.9579. Min Act: -0.1700
Data Index: 4908247 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2730. Min Range: -3.2730
Max Act: 2.9579. Min Act: -0.1700
Data Index: 4025191 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2730. Min Range: -3.2730
Max Act: 2.9420. Min Act: -0.1700
Data Index: 7677645 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2730. Min Range: -3.2730
Max Act: 2.9579. Min Act: -0.1700
Data Index: 4168075 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2730. Min Range: -3.2730
Max Act: 2.9737. Min Act: -0.1700
Data Index: 6938499 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19