Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2705. Min Range: -6.2705
Max Act: 6.2705. Min Act: -0.1700
Data Index: 810846 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2705. Min Range: -6.2705
Max Act: 6.1767. Min Act: -0.1700
Data Index: 1412025 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2705. Min Range: -6.2705
Max Act: 6.1767. Min Act: -0.1700
Data Index: 698096 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2705. Min Range: -6.2705
Max Act: 6.0517. Min Act: -0.1700
Data Index: 2532662 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.9892. Min Act: -0.1700
Data Index: 1805742 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.9267. Min Act: -0.1700
Data Index: 3866224 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.9580. Min Act: -0.1700
Data Index: 1610442 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.8955. Min Act: -0.1700
Data Index: 3184518 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.8955. Min Act: -0.1700
Data Index: 7797164 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.8955. Min Act: -0.1700
Data Index: 4769993 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.8642. Min Act: -0.1700
Data Index: 7353571 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.8330. Min Act: -0.1700
Data Index: 4848399 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.8330. Min Act: -0.1700
Data Index: 8267559 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.8642. Min Act: -0.1700
Data Index: 1591284 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.8017. Min Act: -0.1700
Data Index: 5914073 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.8017. Min Act: -0.1700
Data Index: 6576208 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.8017. Min Act: -0.1700
Data Index: 800378 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.8017. Min Act: -0.1700
Data Index: 4255434 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.7705. Min Act: -0.1700
Data Index: 3339089 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2705. Min Range: -6.2705
Max Act: 5.7705. Min Act: -0.1700
Data Index: 2868422 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19