Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2116 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0346. Min Range: -4.0346
Max Act: 4.0346. Min Act: -0.1700
Data Index: 3771364 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0346. Min Range: -4.0346
Max Act: 4.0033. Min Act: -0.1700
Data Index: 5999344 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.9721. Min Act: -0.1700
Data Index: 7617976 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.9408. Min Act: -0.1700
Data Index: 6659136 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.9721. Min Act: -0.1700
Data Index: 1938865 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.9408. Min Act: -0.1700
Data Index: 5116244 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.9408. Min Act: -0.1700
Data Index: 5893551 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.9408. Min Act: -0.1700
Data Index: 1090397 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.9408. Min Act: -0.1700
Data Index: 4209209 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.8783. Min Act: -0.1700
Data Index: 2217389 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.8783. Min Act: -0.1700
Data Index: 4446746 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.9095. Min Act: -0.1700
Data Index: 5830441 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.9095. Min Act: -0.1700
Data Index: 5655567 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.9095. Min Act: -0.1700
Data Index: 4120249 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.9095. Min Act: -0.1700
Data Index: 3689644 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.8783. Min Act: -0.1700
Data Index: 3567834 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.9408. Min Act: -0.1700
Data Index: 6624749 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.8470. Min Act: -0.1700
Data Index: 2649269 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.8470. Min Act: -0.1700
Data Index: 4291958 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0346. Min Range: -4.0346
Max Act: 3.8783. Min Act: -0.1700
Data Index: 1148533 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19