Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3624 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1849. Min Range: -8.1849
Max Act: 8.1849. Min Act: -0.1700
Data Index: 615476 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1849. Min Range: -8.1849
Max Act: 8.1224. Min Act: -0.1700
Data Index: 8785935 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1849. Min Range: -8.1849
Max Act: 8.0599. Min Act: -0.1700
Data Index: 598799 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1849. Min Range: -8.1849
Max Act: 8.0599. Min Act: -0.1700
Data Index: 615478 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.6849. Min Act: -0.1700
Data Index: 7355944 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.6849. Min Act: -0.1700
Data Index: 4826860 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.6224. Min Act: -0.1700
Data Index: 4486489 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.6224. Min Act: -0.1700
Data Index: 1946580 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.6224. Min Act: -0.1700
Data Index: 3160641 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.6224. Min Act: -0.1700
Data Index: 5849523 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.5599. Min Act: -0.1700
Data Index: 8178769 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.5599. Min Act: -0.1700
Data Index: 4650926 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.5599. Min Act: -0.1700
Data Index: 6637237 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.4349. Min Act: -0.1700
Data Index: 5591215 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.5599. Min Act: -0.1700
Data Index: 8757108 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.4974. Min Act: -0.1700
Data Index: 5284300 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.4974. Min Act: -0.1700
Data Index: 1438598 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.4974. Min Act: -0.1700
Data Index: 2520915 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.4349. Min Act: -0.1700
Data Index: 705703 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1849. Min Range: -8.1849
Max Act: 7.4349. Min Act: -0.1700
Data Index: 6845379 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19