Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3830. Min Range: -4.3830
Max Act: 4.3830. Min Act: -0.1700
Data Index: 5471962 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3830. Min Range: -4.3830
Max Act: 4.1330. Min Act: -0.1700
Data Index: 4618475 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3830. Min Range: -4.3830
Max Act: 4.1017. Min Act: -0.1700
Data Index: 5256968 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3830. Min Range: -4.3830
Max Act: 4.0392. Min Act: -0.1700
Data Index: 3138113 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3830. Min Range: -4.3830
Max Act: 4.0392. Min Act: -0.1700
Data Index: 4272828 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3830. Min Range: -4.3830
Max Act: 4.0392. Min Act: -0.1700
Data Index: 1669324 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3830. Min Range: -4.3830
Max Act: 4.0079. Min Act: -0.1700
Data Index: 4936347 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3830. Min Range: -4.3830
Max Act: 4.0079. Min Act: -0.1700
Data Index: 4167141 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3830. Min Range: -4.3830
Max Act: 3.9767. Min Act: -0.1700
Data Index: 8221342 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3830. Min Range: -4.3830
Max Act: 3.9767. Min Act: -0.1700
Data Index: 7595497 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3830. Min Range: -4.3830
Max Act: 3.9767. Min Act: -0.1700
Data Index: 2329126 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3830. Min Range: -4.3830
Max Act: 3.9767. Min Act: -0.1700
Data Index: 7177689 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3830. Min Range: -4.3830
Max Act: 3.9767. Min Act: -0.1700
Data Index: 6987313 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3830. Min Range: -4.3830
Max Act: 3.9767. Min Act: -0.1700
Data Index: 6876705 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3830. Min Range: -4.3830
Max Act: 3.9767. Min Act: -0.1700
Data Index: 8272241 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3830. Min Range: -4.3830
Max Act: 3.9454. Min Act: -0.1700
Data Index: 1274652 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3830. Min Range: -4.3830
Max Act: 3.9454. Min Act: -0.1700
Data Index: 958186 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3830. Min Range: -4.3830
Max Act: 3.9454. Min Act: -0.1700
Data Index: 1974426 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3830. Min Range: -4.3830
Max Act: 3.9454. Min Act: -0.1700
Data Index: 1938994 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3830. Min Range: -4.3830
Max Act: 3.9454. Min Act: -0.1700
Data Index: 704863 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19