Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1984 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.8463. Min Act: -0.1700
Data Index: 5429739 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.5021. Min Act: -0.1700
Data Index: 4477460 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.4708. Min Act: -0.1700
Data Index: 188750 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.4708. Min Act: -0.1700
Data Index: 3305864 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.4708. Min Act: -0.1700
Data Index: 1311723 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.4708. Min Act: -0.1700
Data Index: 8796407 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.4238. Min Act: -0.1700
Data Index: 4200272 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.4081. Min Act: -0.1700
Data Index: 4783700 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.4238. Min Act: -0.1700
Data Index: 741157 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.4081. Min Act: -0.1700
Data Index: 3584136 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.4394. Min Act: -0.1700
Data Index: 1804459 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.4394. Min Act: -0.1700
Data Index: 1815478 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.4394. Min Act: -0.1700
Data Index: 3129127 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.3767. Min Act: -0.1700
Data Index: 7522749 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.4238. Min Act: -0.1700
Data Index: 1199118 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.3924. Min Act: -0.1700
Data Index: 1453331 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.3924. Min Act: -0.1700
Data Index: 4548064 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.3924. Min Act: -0.1700
Data Index: 4038149 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.3924. Min Act: -0.1700
Data Index: 3727478 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8463. Min Range: -3.8463
Max Act: 3.4081. Min Act: -0.1700
Data Index: 4775170 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19