Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5097 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.4045. Min Range: -15.4045
Max Act: 15.4045. Min Act: -0.1700
Data Index: 4261932 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.4045. Min Range: -15.4045
Max Act: 15.3420. Min Act: -0.1700
Data Index: 6728886 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.9670. Min Act: -0.1700
Data Index: 3882133 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.7170. Min Act: -0.1700
Data Index: 2963644 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.7795. Min Act: -0.1700
Data Index: 6349370 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.7795. Min Act: -0.1700
Data Index: 3956423 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.7795. Min Act: -0.1700
Data Index: 588325 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.7170. Min Act: -0.1700
Data Index: 1783093 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.6545. Min Act: -0.1700
Data Index: 5295050 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.5920. Min Act: -0.1700
Data Index: 4447218 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.5920. Min Act: -0.1700
Data Index: 113790 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.5920. Min Act: -0.1700
Data Index: 1699835 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.5920. Min Act: -0.1700
Data Index: 4261810 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.5295. Min Act: -0.1700
Data Index: 778631 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.4670. Min Act: -0.1700
Data Index: 3366857 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.4045. Min Act: -0.1700
Data Index: 4494319 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.3420. Min Act: -0.1700
Data Index: 1584676 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.4045. Min Act: -0.1700
Data Index: 2502531 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.2795. Min Act: -0.1700
Data Index: 1090004 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.4045. Min Range: -15.4045
Max Act: 14.2795. Min Act: -0.1700
Data Index: 7387152 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19