Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 810 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0436. Min Range: -13.0436
Max Act: 13.0436. Min Act: -0.1700
Data Index: 7680431 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.9811. Min Act: -0.1700
Data Index: 4355945 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.8561. Min Act: -0.1700
Data Index: 2391482 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.7936. Min Act: -0.1700
Data Index: 1057390 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.4811. Min Act: -0.1700
Data Index: 6670248 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.5436. Min Act: -0.1700
Data Index: 172177 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.4186. Min Act: -0.1700
Data Index: 490734 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.4811. Min Act: -0.1700
Data Index: 2243910 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.3561. Min Act: -0.1700
Data Index: 172176 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.2936. Min Act: -0.1700
Data Index: 2194146 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.2311. Min Act: -0.1700
Data Index: 3466786 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.1686. Min Act: -0.1700
Data Index: 2269500 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.2311. Min Act: -0.1700
Data Index: 2468520 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.1686. Min Act: -0.1700
Data Index: 2509577 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.0436. Min Act: -0.1700
Data Index: 6520224 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0436. Min Range: -13.0436
Max Act: 12.0436. Min Act: -0.1700
Data Index: 6098360 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0436. Min Range: -13.0436
Max Act: 11.9811. Min Act: -0.1700
Data Index: 3167151 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0436. Min Range: -13.0436
Max Act: 11.9811. Min Act: -0.1700
Data Index: 4269104 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0436. Min Range: -13.0436
Max Act: 11.9186. Min Act: -0.1700
Data Index: 6068496 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0436. Min Range: -13.0436
Max Act: 11.8561. Min Act: -0.1700
Data Index: 1355759 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19