Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 989 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.4776. Min Act: -0.1700
Data Index: 2429677 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.3214. Min Act: -0.1700
Data Index: 6966098 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.2901. Min Act: -0.1700
Data Index: 4281417 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.2589. Min Act: -0.1700
Data Index: 1674352 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.2276. Min Act: -0.1700
Data Index: 6496717 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.1651. Min Act: -0.1700
Data Index: 5316834 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.1026. Min Act: -0.1700
Data Index: 3237536 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.1026. Min Act: -0.1700
Data Index: 6878009 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.1026. Min Act: -0.1700
Data Index: 4914233 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.1026. Min Act: -0.1700
Data Index: 7173100 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.0713. Min Act: -0.1700
Data Index: 8054008 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.0713. Min Act: -0.1700
Data Index: 234863 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.0401. Min Act: -0.1700
Data Index: 1472183 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.0401. Min Act: -0.1700
Data Index: 8194914 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.0713. Min Act: -0.1700
Data Index: 6900330 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.0088. Min Act: -0.1700
Data Index: 973411 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4776. Min Range: -4.4776
Max Act: 4.0088. Min Act: -0.1700
Data Index: 6943141 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4776. Min Range: -4.4776
Max Act: 3.9776. Min Act: -0.1700
Data Index: 7967278 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4776. Min Range: -4.4776
Max Act: 3.9776. Min Act: -0.1700
Data Index: 223292 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4776. Min Range: -4.4776
Max Act: 3.9776. Min Act: -0.1700
Data Index: 7552031 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19