Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5292 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.3753. Min Act: -0.1700
Data Index: 1752069 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.3440. Min Act: -0.1700
Data Index: 2820010 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.2190. Min Act: -0.1700
Data Index: 3287187 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.2190. Min Act: -0.1700
Data Index: 5393047 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.1878. Min Act: -0.1700
Data Index: 1263433 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.1878. Min Act: -0.1700
Data Index: 655580 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.1565. Min Act: -0.1700
Data Index: 5914317 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.1565. Min Act: -0.1700
Data Index: 428253 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.1253. Min Act: -0.1700
Data Index: 980367 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.1253. Min Act: -0.1700
Data Index: 419168 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.1253. Min Act: -0.1700
Data Index: 4717511 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.0940. Min Act: -0.1700
Data Index: 7079709 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.0940. Min Act: -0.1700
Data Index: 1558559 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.0628. Min Act: -0.1700
Data Index: 4934857 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.0628. Min Act: -0.1700
Data Index: 7088115 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.0628. Min Act: -0.1700
Data Index: 3903168 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.0315. Min Act: -0.1700
Data Index: 7375592 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.0628. Min Act: -0.1700
Data Index: 4844002 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.0003. Min Act: -0.1700
Data Index: 891664 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3753. Min Range: -6.3753
Max Act: 6.0315. Min Act: -0.1700
Data Index: 4545123 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19