Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2283 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1067. Min Range: -6.1067
Max Act: 6.1067. Min Act: -0.1700
Data Index: 516144 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1067. Min Range: -6.1067
Max Act: 6.0755. Min Act: -0.1700
Data Index: 1547062 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1067. Min Range: -6.1067
Max Act: 6.0755. Min Act: -0.1700
Data Index: 2326865 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.9817. Min Act: -0.1700
Data Index: 2391441 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.9817. Min Act: -0.1700
Data Index: 3567799 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.9192. Min Act: -0.1700
Data Index: 6668953 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.9192. Min Act: -0.1700
Data Index: 4815900 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.9192. Min Act: -0.1700
Data Index: 8161009 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.9192. Min Act: -0.1700
Data Index: 520190 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.8880. Min Act: -0.1700
Data Index: 2833594 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.8880. Min Act: -0.1700
Data Index: 1056262 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.8880. Min Act: -0.1700
Data Index: 1088355 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.8567. Min Act: -0.1700
Data Index: 7354524 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.8567. Min Act: -0.1700
Data Index: 1705690 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.8255. Min Act: -0.1700
Data Index: 1073135 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.8255. Min Act: -0.1700
Data Index: 2342876 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.8255. Min Act: -0.1700
Data Index: 2850226 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.7942. Min Act: -0.1700
Data Index: 296510 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.7942. Min Act: -0.1700
Data Index: 1161452 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1067. Min Range: -6.1067
Max Act: 5.7942. Min Act: -0.1700
Data Index: 750650 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19