Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1502 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.7885. Min Act: -0.1700
Data Index: 7145794 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.5072. Min Act: -0.1700
Data Index: 803215 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.4760. Min Act: -0.1700
Data Index: 8725238 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.4135. Min Act: -0.1700
Data Index: 4378150 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.4135. Min Act: -0.1700
Data Index: 6183684 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.3510. Min Act: -0.1700
Data Index: 700519 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.3510. Min Act: -0.1700
Data Index: 6394833 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.3510. Min Act: -0.1700
Data Index: 5480290 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.2572. Min Act: -0.1700
Data Index: 8189382 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.1947. Min Act: -0.1700
Data Index: 5626103 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.2572. Min Act: -0.1700
Data Index: 5626105 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.2572. Min Act: -0.1700
Data Index: 4809246 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.2260. Min Act: -0.1700
Data Index: 4806930 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.2885. Min Act: -0.1700
Data Index: 3845341 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.2572. Min Act: -0.1700
Data Index: 2792793 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.1635. Min Act: -0.1700
Data Index: 2310822 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.1635. Min Act: -0.1700
Data Index: 2466495 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.1635. Min Act: -0.1700
Data Index: 2342873 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.1947. Min Act: -0.1700
Data Index: 8361774 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7885. Min Range: -5.7885
Max Act: 5.1322. Min Act: -0.1700
Data Index: 4343486 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19