Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2115 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1786. Min Range: -6.1786
Max Act: 6.1786. Min Act: -0.1700
Data Index: 5988913 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1786. Min Range: -6.1786
Max Act: 6.0223. Min Act: -0.1700
Data Index: 8173110 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1786. Min Range: -6.1786
Max Act: 6.0223. Min Act: -0.1700
Data Index: 2898740 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1786. Min Range: -6.1786
Max Act: 6.0223. Min Act: -0.1700
Data Index: 2920240 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.9598. Min Act: -0.1700
Data Index: 7574979 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.9598. Min Act: -0.1700
Data Index: 2196833 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.9598. Min Act: -0.1700
Data Index: 3349942 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.9911. Min Act: -0.1700
Data Index: 6151496 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.8973. Min Act: -0.1700
Data Index: 2650642 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.9598. Min Act: -0.1700
Data Index: 5000495 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.9286. Min Act: -0.1700
Data Index: 7712129 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.8973. Min Act: -0.1700
Data Index: 8139080 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.8973. Min Act: -0.1700
Data Index: 1770754 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.8973. Min Act: -0.1700
Data Index: 1742046 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.8973. Min Act: -0.1700
Data Index: 1248586 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.8036. Min Act: -0.1700
Data Index: 5921005 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.8348. Min Act: -0.1700
Data Index: 4741278 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.8348. Min Act: -0.1700
Data Index: 2116154 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.8348. Min Act: -0.1700
Data Index: 1233240 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1786. Min Range: -6.1786
Max Act: 5.8036. Min Act: -0.1700
Data Index: 949507 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19