Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.7104. Min Act: -0.1700
Data Index: 5629635 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.7104. Min Act: -0.1700
Data Index: 2317185 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.6791. Min Act: -0.1700
Data Index: 2317186 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.6166. Min Act: -0.1700
Data Index: 5593958 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.5854. Min Act: -0.1700
Data Index: 6838661 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.5854. Min Act: -0.1700
Data Index: 5919304 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.5854. Min Act: -0.1700
Data Index: 5593960 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.5541. Min Act: -0.1700
Data Index: 5593955 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.5854. Min Act: -0.1700
Data Index: 5919298 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.5541. Min Act: -0.1700
Data Index: 617328 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.5541. Min Act: -0.1700
Data Index: 1412761 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.5854. Min Act: -0.1700
Data Index: 6838660 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.5229. Min Act: -0.1700
Data Index: 1193149 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.4604. Min Act: -0.1700
Data Index: 6838662 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.4916. Min Act: -0.1700
Data Index: 298389 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.4916. Min Act: -0.1700
Data Index: 5629631 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.4916. Min Act: -0.1700
Data Index: 3852628 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.4291. Min Act: -0.1700
Data Index: 3014017 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.4916. Min Act: -0.1700
Data Index: 5919312 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7104. Min Range: -5.7104
Max Act: 5.4604. Min Act: -0.1700
Data Index: 5593957 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19