Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6128 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6668. Min Range: -10.6668
Max Act: 10.6668. Min Act: -0.1700
Data Index: 8528511 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6668. Min Range: -10.6668
Max Act: 10.4793. Min Act: -0.1700
Data Index: 4452312 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6668. Min Range: -10.6668
Max Act: 10.4168. Min Act: -0.1700
Data Index: 3182284 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6668. Min Range: -10.6668
Max Act: 10.1043. Min Act: -0.1700
Data Index: 4329974 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6668. Min Range: -10.6668
Max Act: 10.1668. Min Act: -0.1700
Data Index: 1946202 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6668. Min Range: -10.6668
Max Act: 10.1043. Min Act: -0.1700
Data Index: 8591958 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6668. Min Range: -10.6668
Max Act: 10.0418. Min Act: -0.1700
Data Index: 1581407 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6668. Min Range: -10.6668
Max Act: 9.9793. Min Act: -0.1700
Data Index: 8535051 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6668. Min Range: -10.6668
Max Act: 9.9793. Min Act: -0.1700
Data Index: 2446852 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6668. Min Range: -10.6668
Max Act: 9.9168. Min Act: -0.1700
Data Index: 7340164 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6668. Min Range: -10.6668
Max Act: 9.9168. Min Act: -0.1700
Data Index: 2446855 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6668. Min Range: -10.6668
Max Act: 9.8543. Min Act: -0.1700
Data Index: 2785064 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6668. Min Range: -10.6668
Max Act: 9.8543. Min Act: -0.1700
Data Index: 4874638 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6668. Min Range: -10.6668
Max Act: 9.8543. Min Act: -0.1700
Data Index: 1663010 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6668. Min Range: -10.6668
Max Act: 9.7918. Min Act: -0.1700
Data Index: 867741 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6668. Min Range: -10.6668
Max Act: 9.7293. Min Act: -0.1700
Data Index: 1750761 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6668. Min Range: -10.6668
Max Act: 9.7293. Min Act: -0.1700
Data Index: 4500163 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6668. Min Range: -10.6668
Max Act: 9.7918. Min Act: -0.1700
Data Index: 3129762 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6668. Min Range: -10.6668
Max Act: 9.7293. Min Act: -0.1700
Data Index: 1737120 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6668. Min Range: -10.6668
Max Act: 9.7293. Min Act: -0.1700
Data Index: 7958137 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19