Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 138 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.3704. Min Act: -0.1700
Data Index: 7089714 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.3704. Min Act: -0.1700
Data Index: 6528856 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.3391. Min Act: -0.1700
Data Index: 5792048 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.3391. Min Act: -0.1700
Data Index: 5472369 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.3391. Min Act: -0.1700
Data Index: 6987334 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.3079. Min Act: -0.1700
Data Index: 3927455 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2766. Min Act: -0.1682
Data Index: 1588150 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2766. Min Act: -0.1699
Data Index: 169122 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2766. Min Act: -0.1699
Data Index: 7530923 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2454. Min Act: -0.1700
Data Index: 2624635 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2454. Min Act: -0.1700
Data Index: 2147284 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2454. Min Act: -0.1700
Data Index: 3873586 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2141. Min Act: -0.1700
Data Index: 8210970 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2454. Min Act: -0.1700
Data Index: 4327796 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2454. Min Act: -0.1696
Data Index: 6617164 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2454. Min Act: -0.1700
Data Index: 6200470 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2766. Min Act: -0.1700
Data Index: 872581 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2454. Min Act: -0.1693
Data Index: 2130426 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2454. Min Act: -0.1685
Data Index: 1406895 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3704. Min Range: -5.3704
Max Act: 5.2141. Min Act: -0.1699
Data Index: 5116434 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19