Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2329 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5026. Min Range: -6.5026
Max Act: 6.5026. Min Act: -0.1700
Data Index: 2107662 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5026. Min Range: -6.5026
Max Act: 6.4401. Min Act: -0.1700
Data Index: 1383092 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5026. Min Range: -6.5026
Max Act: 6.1588. Min Act: -0.1700
Data Index: 3420749 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5026. Min Range: -6.5026
Max Act: 6.0963. Min Act: -0.1700
Data Index: 922408 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5026. Min Range: -6.5026
Max Act: 6.1276. Min Act: -0.1700
Data Index: 6802509 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5026. Min Range: -6.5026
Max Act: 6.0651. Min Act: -0.1700
Data Index: 5768466 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.9713. Min Act: -0.1700
Data Index: 2839682 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.9401. Min Act: -0.1700
Data Index: 493754 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.9401. Min Act: -0.1700
Data Index: 5432321 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.8776. Min Act: -0.1700
Data Index: 7285648 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.8776. Min Act: -0.1700
Data Index: 8446072 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.8463. Min Act: -0.1700
Data Index: 5994161 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.8463. Min Act: -0.1700
Data Index: 4244633 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.7526. Min Act: -0.1700
Data Index: 5293567 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.7526. Min Act: -0.1700
Data Index: 6818494 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.7213. Min Act: -0.1700
Data Index: 5360514 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.6901. Min Act: -0.1700
Data Index: 210598 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.6901. Min Act: -0.1700
Data Index: 5461408 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.7213. Min Act: -0.1700
Data Index: 517206 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5026. Min Range: -6.5026
Max Act: 5.6901. Min Act: -0.1700
Data Index: 2888548 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19