Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2955 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0062. Min Range: -7.0062
Max Act: 7.0062. Min Act: -0.1700
Data Index: 1333231 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.9750. Min Act: -0.1700
Data Index: 4790352 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.9750. Min Act: -0.1700
Data Index: 833355 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.9437. Min Act: -0.1700
Data Index: 6263242 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.8812. Min Act: -0.1700
Data Index: 4231632 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.8500. Min Act: -0.1700
Data Index: 4189299 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.7875. Min Act: -0.1700
Data Index: 6141127 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.7250. Min Act: -0.1700
Data Index: 3425379 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.6625. Min Act: -0.1700
Data Index: 4889288 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.6625. Min Act: -0.1700
Data Index: 5061641 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.6312. Min Act: -0.1700
Data Index: 7796289 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.6312. Min Act: -0.1700
Data Index: 7976390 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.5375. Min Act: -0.1700
Data Index: 420931 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.6000. Min Act: -0.1700
Data Index: 5694133 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.5687. Min Act: -0.1700
Data Index: 328431 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.6000. Min Act: -0.1700
Data Index: 6529647 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.5375. Min Act: -0.1700
Data Index: 1763907 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.5375. Min Act: -0.1700
Data Index: 4551498 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.5062. Min Act: -0.1700
Data Index: 4777646 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0062. Min Range: -7.0062
Max Act: 6.5062. Min Act: -0.1700
Data Index: 6464098 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19