Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3719 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0331. Min Range: -7.0331
Max Act: 7.0331. Min Act: -0.1700
Data Index: 403746 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0331. Min Range: -7.0331
Max Act: 7.0331. Min Act: -0.1700
Data Index: 3664753 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.9394. Min Act: -0.1700
Data Index: 7546999 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.9081. Min Act: -0.1700
Data Index: 4389192 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.8769. Min Act: -0.1700
Data Index: 2620303 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.8144. Min Act: -0.1700
Data Index: 6581996 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.8144. Min Act: -0.1700
Data Index: 4308082 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.7831. Min Act: -0.1700
Data Index: 1971673 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.7519. Min Act: -0.1700
Data Index: 3000037 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.7206. Min Act: -0.1700
Data Index: 8634002 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.6894. Min Act: -0.1700
Data Index: 284336 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.6581. Min Act: -0.1700
Data Index: 1034892 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.6269. Min Act: -0.1700
Data Index: 6690908 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.5956. Min Act: -0.1700
Data Index: 925038 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.5644. Min Act: -0.1700
Data Index: 8392607 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.5331. Min Act: -0.1700
Data Index: 8253228 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.5644. Min Act: -0.1700
Data Index: 7241302 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.5644. Min Act: -0.1700
Data Index: 6934858 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.5644. Min Act: -0.1700
Data Index: 7578009 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0331. Min Range: -7.0331
Max Act: 6.5644. Min Act: -0.1700
Data Index: 6924042 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19