Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 920 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0934. Min Range: -4.0934
Max Act: 4.0934. Min Act: -0.1700
Data Index: 6622724 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.8745. Min Act: -0.1700
Data Index: 631744 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.8745. Min Act: -0.1700
Data Index: 5321492 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.8276. Min Act: -0.1700
Data Index: 2593949 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.8433. Min Act: -0.1700
Data Index: 8424287 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.8276. Min Act: -0.1700
Data Index: 6130091 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.7651. Min Act: -0.1700
Data Index: 5649287 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.7651. Min Act: -0.1700
Data Index: 2401487 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.7494. Min Act: -0.1700
Data Index: 8720101 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.7182. Min Act: -0.1700
Data Index: 2342557 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.7182. Min Act: -0.1700
Data Index: 3863312 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.7025. Min Act: -0.1700
Data Index: 4701579 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.7182. Min Act: -0.1700
Data Index: 2629545 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.6712. Min Act: -0.1700
Data Index: 1857419 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.6243. Min Act: -0.1700
Data Index: 651598 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.6399. Min Act: -0.1700
Data Index: 1560535 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.6243. Min Act: -0.1700
Data Index: 1291132 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.6243. Min Act: -0.1700
Data Index: 3526497 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.6086. Min Act: -0.1700
Data Index: 4247206 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0934. Min Range: -4.0934
Max Act: 3.5773. Min Act: -0.1700
Data Index: 2309973 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19