Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.3391. Min Act: -0.1700
Data Index: 1147723 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.3391. Min Act: -0.1700
Data Index: 2746635 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.2766. Min Act: -0.1700
Data Index: 114456 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.2453. Min Act: -0.1700
Data Index: 2866482 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.2141. Min Act: -0.1700
Data Index: 5271905 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.1516. Min Act: -0.1700
Data Index: 4235974 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.0891. Min Act: -0.1700
Data Index: 197028 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.0891. Min Act: -0.1700
Data Index: 7571246 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.0891. Min Act: -0.1700
Data Index: 47727 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.0578. Min Act: -0.1700
Data Index: 7532266 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.0891. Min Act: -0.1700
Data Index: 2645644 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.0578. Min Act: -0.1700
Data Index: 3375370 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.0266. Min Act: -0.1700
Data Index: 6912231 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3391. Min Range: -5.3391
Max Act: 4.9953. Min Act: -0.1700
Data Index: 5822877 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.0266. Min Act: -0.1700
Data Index: 8468494 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3391. Min Range: -5.3391
Max Act: 5.0266. Min Act: -0.1700
Data Index: 991131 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3391. Min Range: -5.3391
Max Act: 4.9953. Min Act: -0.1700
Data Index: 7605242 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3391. Min Range: -5.3391
Max Act: 4.9953. Min Act: -0.1700
Data Index: 956703 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3391. Min Range: -5.3391
Max Act: 4.9953. Min Act: -0.1700
Data Index: 1879117 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3391. Min Range: -5.3391
Max Act: 4.9641. Min Act: -0.1700
Data Index: 1410297 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19