Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 786 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.7291. Min Act: -0.1700
Data Index: 4975981 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.7604. Min Act: -0.1700
Data Index: 571089 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.6979. Min Act: -0.1700
Data Index: 6442802 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.6666. Min Act: -0.1700
Data Index: 3167627 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.6041. Min Act: -0.1700
Data Index: 3136655 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.5729. Min Act: -0.1700
Data Index: 4455308 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.5729. Min Act: -0.1700
Data Index: 129284 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.5729. Min Act: -0.1700
Data Index: 3719034 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.6041. Min Act: -0.1700
Data Index: 3071601 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.5104. Min Act: -0.1700
Data Index: 6982902 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.5104. Min Act: -0.1700
Data Index: 270035 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.5729. Min Act: -0.1700
Data Index: 7390519 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.4791. Min Act: -0.1700
Data Index: 6184954 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.4791. Min Act: -0.1700
Data Index: 4445935 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.4479. Min Act: -0.1700
Data Index: 3715182 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.4479. Min Act: -0.1700
Data Index: 7153760 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.4479. Min Act: -0.1700
Data Index: 6775606 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.4791. Min Act: -0.1700
Data Index: 6542577 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.4479. Min Act: -0.1700
Data Index: 5604501 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7604. Min Range: -6.7604
Max Act: 6.4166. Min Act: -0.1700
Data Index: 1602858 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19