Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1935 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.5779. Min Act: -0.1700
Data Index: 2182597 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.4529. Min Act: -0.1700
Data Index: 237113 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.3279. Min Act: -0.1700
Data Index: 378724 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.2654. Min Act: -0.1700
Data Index: 2176690 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.3279. Min Act: -0.1700
Data Index: 1118171 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.2654. Min Act: -0.1700
Data Index: 485218 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.2341. Min Act: -0.1700
Data Index: 5600171 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.1716. Min Act: -0.1700
Data Index: 724460 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.1716. Min Act: -0.1700
Data Index: 4777728 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.1404. Min Act: -0.1700
Data Index: 1318284 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.1716. Min Act: -0.1700
Data Index: 5374365 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.1091. Min Act: -0.1700
Data Index: 5303729 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.0779. Min Act: -0.1700
Data Index: 1746195 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.0779. Min Act: -0.1700
Data Index: 4121958 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.0466. Min Act: -0.1700
Data Index: 904625 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.0466. Min Act: -0.1700
Data Index: 2071756 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.0154. Min Act: -0.1700
Data Index: 3710910 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.0154. Min Act: -0.1700
Data Index: 521544 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5779. Min Range: -7.5779
Max Act: 6.9841. Min Act: -0.1700
Data Index: 6284754 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5779. Min Range: -7.5779
Max Act: 7.0154. Min Act: -0.1700
Data Index: 4642044 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19