Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2626 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0422. Min Range: -2.0422
Max Act: 2.0422. Min Act: -0.1700
Data Index: 1711578 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9916. Min Act: -0.1700
Data Index: 3516057 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9746. Min Act: -0.1700
Data Index: 3229137 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9577. Min Act: -0.1700
Data Index: 8724063 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9577. Min Act: -0.1700
Data Index: 7368040 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9407. Min Act: -0.1700
Data Index: 122043 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9492. Min Act: -0.1700
Data Index: 5272948 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9492. Min Act: -0.1700
Data Index: 1109543 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9492. Min Act: -0.1700
Data Index: 428466 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9237. Min Act: -0.1700
Data Index: 6111180 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9407. Min Act: -0.1700
Data Index: 145300 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9322. Min Act: -0.1700
Data Index: 8396378 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9067. Min Act: -0.1700
Data Index: 4235422 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9237. Min Act: -0.1700
Data Index: 7636903 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9237. Min Act: -0.1700
Data Index: 8414161 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9067. Min Act: -0.1700
Data Index: 153865 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9067. Min Act: -0.1700
Data Index: 2453250 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9067. Min Act: -0.1700
Data Index: 7417955 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9152. Min Act: -0.1700
Data Index: 6103972 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0422. Min Range: -2.0422
Max Act: 1.9237. Min Act: -0.1700
Data Index: 2403662 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19