Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2202 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.4795. Min Act: -0.1700
Data Index: 5183564 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.4170. Min Act: -0.1700
Data Index: 2378064 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.3858. Min Act: -0.1700
Data Index: 6600519 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.3545. Min Act: -0.1700
Data Index: 5132863 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.3545. Min Act: -0.1700
Data Index: 2133692 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.2608. Min Act: -0.1700
Data Index: 1651381 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.2608. Min Act: -0.1700
Data Index: 7901007 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.2608. Min Act: -0.1700
Data Index: 2894655 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.1983. Min Act: -0.1700
Data Index: 6270515 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.1983. Min Act: -0.1700
Data Index: 5245239 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.2295. Min Act: -0.1700
Data Index: 1487458 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.1670. Min Act: -0.1700
Data Index: 1940083 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.1670. Min Act: -0.1700
Data Index: 7780641 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.1670. Min Act: -0.1700
Data Index: 8453453 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.1670. Min Act: -0.1700
Data Index: 6034722 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.1358. Min Act: -0.1700
Data Index: 4333744 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.1358. Min Act: -0.1700
Data Index: 6328999 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.1358. Min Act: -0.1700
Data Index: 6766793 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.1045. Min Act: -0.1700
Data Index: 2707313 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4795. Min Range: -7.4795
Max Act: 7.1045. Min Act: -0.1700
Data Index: 6921754 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19