Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2440 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.9547. Min Act: -0.1700
Data Index: 6293143 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.9705. Min Act: -0.1700
Data Index: 3874903 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.9230. Min Act: -0.1700
Data Index: 1771461 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.9071. Min Act: -0.1700
Data Index: 8595768 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.8754. Min Act: -0.1700
Data Index: 2675462 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.8754. Min Act: -0.1700
Data Index: 7379088 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.8437. Min Act: -0.1700
Data Index: 2604110 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.8437. Min Act: -0.1700
Data Index: 7722264 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.8278. Min Act: -0.1700
Data Index: 3604755 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.8278. Min Act: -0.1700
Data Index: 1151048 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.8118. Min Act: -0.1700
Data Index: 1461629 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.8278. Min Act: -0.1700
Data Index: 4736690 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.7800. Min Act: -0.1700
Data Index: 2194958 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.7959. Min Act: -0.1700
Data Index: 6390827 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.7800. Min Act: -0.1700
Data Index: 2599296 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.7481. Min Act: -0.1700
Data Index: 2153025 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.7481. Min Act: -0.1700
Data Index: 7768852 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.7481. Min Act: -0.1700
Data Index: 4790565 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.7321. Min Act: -0.1700
Data Index: 739481 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9705. Min Range: -2.9705
Max Act: 2.7161. Min Act: -0.1700
Data Index: 5839826 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19