Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1645 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0607. Min Range: -6.0607
Max Act: 6.0607. Min Act: -0.1700
Data Index: 3721289 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0607. Min Range: -6.0607
Max Act: 6.0295. Min Act: -0.1700
Data Index: 2035580 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.9357. Min Act: -0.1700
Data Index: 7118313 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.9045. Min Act: -0.1700
Data Index: 6643041 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.8107. Min Act: -0.1700
Data Index: 6829413 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.8420. Min Act: -0.1700
Data Index: 7422893 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.8420. Min Act: -0.1700
Data Index: 7611379 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.7795. Min Act: -0.1700
Data Index: 1434365 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.7482. Min Act: -0.1700
Data Index: 6505958 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.7482. Min Act: -0.1700
Data Index: 6493929 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.7482. Min Act: -0.1700
Data Index: 5158182 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.7170. Min Act: -0.1700
Data Index: 1118525 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.7170. Min Act: -0.1700
Data Index: 8156642 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.6857. Min Act: -0.1700
Data Index: 6780056 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.6857. Min Act: -0.1700
Data Index: 7680671 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.6857. Min Act: -0.1700
Data Index: 8499634 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.6545. Min Act: -0.1700
Data Index: 7155151 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.6232. Min Act: -0.1700
Data Index: 7375464 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.5920. Min Act: -0.1700
Data Index: 6056355 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0607. Min Range: -6.0607
Max Act: 5.5920. Min Act: -0.1700
Data Index: 2577638 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19