Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 541 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.8858. Min Act: -0.1700
Data Index: 4078661 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.8858. Min Act: -0.1700
Data Index: 1348776 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.8012. Min Act: -0.1700
Data Index: 5216269 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7844. Min Act: -0.1700
Data Index: 3040373 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7844. Min Act: -0.1700
Data Index: 7474544 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7844. Min Act: -0.1700
Data Index: 3604889 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7512. Min Act: -0.1700
Data Index: 7571778 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7512. Min Act: -0.1700
Data Index: 5783931 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7512. Min Act: -0.1700
Data Index: 4458393 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7346. Min Act: -0.1699
Data Index: 8732858 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7346. Min Act: -0.1700
Data Index: 853934 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7346. Min Act: -0.1700
Data Index: 8811694 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7346. Min Act: -0.1700
Data Index: 3799686 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7346. Min Act: -0.1699
Data Index: 5723020 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7182. Min Act: -0.1697
Data Index: 4225652 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7182. Min Act: -0.1700
Data Index: 3018162 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7182. Min Act: -0.1700
Data Index: 555337 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7182. Min Act: -0.1700
Data Index: 3029270 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7346. Min Act: -0.1700
Data Index: 7927621 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7182. Min Act: -0.1700
Data Index: 271571 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19