Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4512 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0369. Min Range: -9.0369
Max Act: 9.0369. Min Act: -0.1700
Data Index: 900620 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.5994. Min Act: -0.1700
Data Index: 600 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.5369. Min Act: -0.1700
Data Index: 2818287 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.4744. Min Act: -0.1700
Data Index: 866459 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.4744. Min Act: -0.1700
Data Index: 999740 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.4744. Min Act: -0.1700
Data Index: 2686932 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.2869. Min Act: -0.1700
Data Index: 2694537 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.2244. Min Act: -0.1700
Data Index: 8489837 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.2869. Min Act: -0.1700
Data Index: 7081498 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.2244. Min Act: -0.1700
Data Index: 4698284 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.2244. Min Act: -0.1700
Data Index: 5586978 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.2244. Min Act: -0.1700
Data Index: 5033366 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.2244. Min Act: -0.1700
Data Index: 3658015 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.2244. Min Act: -0.1700
Data Index: 2089233 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.1619. Min Act: -0.1700
Data Index: 2926580 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.0994. Min Act: -0.1700
Data Index: 4746351 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.0994. Min Act: -0.1700
Data Index: 5056262 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.0369. Min Act: -0.1700
Data Index: 3934257 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.0369. Min Act: -0.1700
Data Index: 2139354 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0369. Min Range: -9.0369
Max Act: 8.0369. Min Act: -0.1700
Data Index: 4680230 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19