Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3439 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.9067. Min Act: -0.1700
Data Index: 7377741 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.7816. Min Act: -0.1700
Data Index: 1761504 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.7816. Min Act: -0.1700
Data Index: 951838 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.7816. Min Act: -0.1700
Data Index: 2842175 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.7347. Min Act: -0.1700
Data Index: 1130818 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.7347. Min Act: -0.1700
Data Index: 1235321 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.7034. Min Act: -0.1700
Data Index: 951832 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.6408. Min Act: -0.1700
Data Index: 7786049 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.6408. Min Act: -0.1700
Data Index: 4015530 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.6252. Min Act: -0.1700
Data Index: 5155665 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.6095. Min Act: -0.1700
Data Index: 3506214 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.5782. Min Act: -0.1700
Data Index: 8122633 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.5782. Min Act: -0.1700
Data Index: 1761505 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.5939. Min Act: -0.1700
Data Index: 4104861 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.5625. Min Act: -0.1700
Data Index: 6016531 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.5625. Min Act: -0.1700
Data Index: 5754557 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.5469. Min Act: -0.1700
Data Index: 7850202 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.5312. Min Act: -0.1700
Data Index: 4775917 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.4999. Min Act: -0.1700
Data Index: 951835 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9067. Min Range: -3.9067
Max Act: 3.5156. Min Act: -0.1700
Data Index: 951836 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19