Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0972. Min Range: -6.0972
Max Act: 6.0972. Min Act: -0.1700
Data Index: 1449878 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.9722. Min Act: -0.1700
Data Index: 3147188 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.9409. Min Act: -0.1700
Data Index: 4751945 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.8784. Min Act: -0.1700
Data Index: 7264843 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.8784. Min Act: -0.1700
Data Index: 2322425 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.8784. Min Act: -0.1700
Data Index: 5333998 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.7847. Min Act: -0.1700
Data Index: 3916139 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.8159. Min Act: -0.1700
Data Index: 4048670 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.7847. Min Act: -0.1700
Data Index: 4054789 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.7222. Min Act: -0.1700
Data Index: 4429167 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.7222. Min Act: -0.1700
Data Index: 5898341 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.7222. Min Act: -0.1700
Data Index: 4250969 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.7222. Min Act: -0.1700
Data Index: 7798590 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.6597. Min Act: -0.1700
Data Index: 6570386 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.6909. Min Act: -0.1700
Data Index: 7661979 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.7222. Min Act: -0.1700
Data Index: 7631960 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.7222. Min Act: -0.1700
Data Index: 857527 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.6909. Min Act: -0.1700
Data Index: 5038875 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.6597. Min Act: -0.1700
Data Index: 5781247 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0972. Min Range: -6.0972
Max Act: 5.6597. Min Act: -0.1700
Data Index: 6396595 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19