Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3233 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.8287. Min Act: -0.1700
Data Index: 7879623 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.7349. Min Act: -0.1700
Data Index: 6747066 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.6724. Min Act: -0.1700
Data Index: 8398934 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.6724. Min Act: -0.1700
Data Index: 1050284 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.6099. Min Act: -0.1700
Data Index: 6674609 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5787. Min Act: -0.1700
Data Index: 383181 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5787. Min Act: -0.1700
Data Index: 6694007 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5787. Min Act: -0.1700
Data Index: 3498698 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5787. Min Act: -0.1700
Data Index: 669193 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5474. Min Act: -0.1700
Data Index: 6568766 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5474. Min Act: -0.1700
Data Index: 2619146 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5474. Min Act: -0.1700
Data Index: 5861393 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5474. Min Act: -0.1700
Data Index: 2819385 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.4849. Min Act: -0.1700
Data Index: 1862126 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5162. Min Act: -0.1700
Data Index: 3265046 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5162. Min Act: -0.1700
Data Index: 7168075 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5162. Min Act: -0.1700
Data Index: 1609847 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5474. Min Act: -0.1700
Data Index: 4599684 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5162. Min Act: -0.1700
Data Index: 3403385 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8287. Min Range: -4.8287
Max Act: 4.5162. Min Act: -0.1700
Data Index: 1784898 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19