Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7254. Min Range: -9.7254
Max Act: 9.7254. Min Act: -0.1700
Data Index: 1090022 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7254. Min Range: -9.7254
Max Act: 9.5379. Min Act: -0.1700
Data Index: 686112 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7254. Min Range: -9.7254
Max Act: 9.6004. Min Act: -0.1700
Data Index: 3873721 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7254. Min Range: -9.7254
Max Act: 9.3504. Min Act: -0.1700
Data Index: 1090030 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7254. Min Range: -9.7254
Max Act: 9.2879. Min Act: -0.1700
Data Index: 8468878 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7254. Min Range: -9.7254
Max Act: 9.2254. Min Act: -0.1700
Data Index: 3474192 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7254. Min Range: -9.7254
Max Act: 9.1629. Min Act: -0.1700
Data Index: 1090023 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7254. Min Range: -9.7254
Max Act: 9.1629. Min Act: -0.1700
Data Index: 3336339 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7254. Min Range: -9.7254
Max Act: 9.1004. Min Act: -0.1700
Data Index: 2081517 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7254. Min Range: -9.7254
Max Act: 9.0379. Min Act: -0.1700
Data Index: 65629 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7254. Min Range: -9.7254
Max Act: 9.0379. Min Act: -0.1700
Data Index: 1570159 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7254. Min Range: -9.7254
Max Act: 8.9129. Min Act: -0.1700
Data Index: 8662749 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7254. Min Range: -9.7254
Max Act: 8.9129. Min Act: -0.1700
Data Index: 1090031 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7254. Min Range: -9.7254
Max Act: 8.9129. Min Act: -0.1700
Data Index: 3747883 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7254. Min Range: -9.7254
Max Act: 8.9129. Min Act: -0.1700
Data Index: 610621 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7254. Min Range: -9.7254
Max Act: 8.8504. Min Act: -0.1700
Data Index: 5935460 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7254. Min Range: -9.7254
Max Act: 8.8504. Min Act: -0.1700
Data Index: 2081521 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7254. Min Range: -9.7254
Max Act: 8.7879. Min Act: -0.1700
Data Index: 2081514 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7254. Min Range: -9.7254
Max Act: 8.8504. Min Act: -0.1700
Data Index: 8493571 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7254. Min Range: -9.7254
Max Act: 8.9129. Min Act: -0.1700
Data Index: 1216758 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19