Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3110 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2047. Min Range: -6.2047
Max Act: 6.2047. Min Act: -0.1700
Data Index: 1741321 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2047. Min Range: -6.2047
Max Act: 6.1734. Min Act: -0.1700
Data Index: 407490 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2047. Min Range: -6.2047
Max Act: 6.1734. Min Act: -0.1698
Data Index: 7773285 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2047. Min Range: -6.2047
Max Act: 6.1109. Min Act: -0.1700
Data Index: 1435132 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2047. Min Range: -6.2047
Max Act: 6.1734. Min Act: -0.1700
Data Index: 7598431 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2047. Min Range: -6.2047
Max Act: 6.0797. Min Act: -0.1700
Data Index: 4073374 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2047. Min Range: -6.2047
Max Act: 6.0797. Min Act: -0.1700
Data Index: 8392174 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2047. Min Range: -6.2047
Max Act: 6.0484. Min Act: -0.1700
Data Index: 2956035 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2047. Min Range: -6.2047
Max Act: 6.0484. Min Act: -0.1700
Data Index: 2434674 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2047. Min Range: -6.2047
Max Act: 6.0172. Min Act: -0.1700
Data Index: 4680272 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2047. Min Range: -6.2047
Max Act: 6.0172. Min Act: -0.1700
Data Index: 6308581 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.9859. Min Act: -0.1700
Data Index: 4702797 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.9859. Min Act: -0.1699
Data Index: 3193364 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.9234. Min Act: -0.1700
Data Index: 4687779 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.9547. Min Act: -0.1700
Data Index: 3521894 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.9547. Min Act: -0.1700
Data Index: 4323253 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.9547. Min Act: -0.1700
Data Index: 5613734 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.9234. Min Act: -0.1700
Data Index: 5869175 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.8922. Min Act: -0.1700
Data Index: 1533919 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.9234. Min Act: -0.1700
Data Index: 5227672 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19