Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.9911. Min Act: -0.1700
Data Index: 7335219 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.8349. Min Act: -0.1700
Data Index: 8140644 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.7724. Min Act: -0.1700
Data Index: 1286351 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.7411. Min Act: -0.1700
Data Index: 6159192 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.6474. Min Act: -0.1700
Data Index: 321929 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.6786. Min Act: -0.1700
Data Index: 3272170 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.6474. Min Act: -0.1700
Data Index: 7179324 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.6474. Min Act: -0.1700
Data Index: 3050980 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5536. Min Act: -0.1700
Data Index: 7452463 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5849. Min Act: -0.1700
Data Index: 8376693 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5849. Min Act: -0.1700
Data Index: 5114273 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5849. Min Act: -0.1700
Data Index: 4270267 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.6161. Min Act: -0.1700
Data Index: 2198742 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5536. Min Act: -0.1700
Data Index: 710298 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5536. Min Act: -0.1700
Data Index: 858394 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5224. Min Act: -0.1700
Data Index: 827363 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5536. Min Act: -0.1700
Data Index: 5834959 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5536. Min Act: -0.1700
Data Index: 746428 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5536. Min Act: -0.1700
Data Index: 4030271 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5536. Min Act: -0.1700
Data Index: 4164273 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19