Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4065 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0045. Min Range: -5.0045
Max Act: 5.0045. Min Act: -0.1700
Data Index: 5545920 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.9420. Min Act: -0.1700
Data Index: 4027028 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.9107. Min Act: -0.1700
Data Index: 6459818 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.8482. Min Act: -0.1700
Data Index: 3036708 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.8482. Min Act: -0.1700
Data Index: 4247203 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.8482. Min Act: -0.1700
Data Index: 279513 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.8170. Min Act: -0.1700
Data Index: 3602939 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.8170. Min Act: -0.1700
Data Index: 5654172 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.7857. Min Act: -0.1700
Data Index: 755786 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.7857. Min Act: -0.1700
Data Index: 482572 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.7857. Min Act: -0.1700
Data Index: 1378116 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.7545. Min Act: -0.1700
Data Index: 469342 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.7545. Min Act: -0.1700
Data Index: 5255478 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.6920. Min Act: -0.1700
Data Index: 3886025 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.7232. Min Act: -0.1700
Data Index: 3276600 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.7232. Min Act: -0.1700
Data Index: 1870011 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.7232. Min Act: -0.1700
Data Index: 6496034 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.7545. Min Act: -0.1700
Data Index: 3837008 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.7232. Min Act: -0.1700
Data Index: 1190204 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0045. Min Range: -5.0045
Max Act: 4.6607. Min Act: -0.1700
Data Index: 1350423 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19