Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1785 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.9391. Min Act: -0.1700
Data Index: 4494313 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.6891. Min Act: -0.1700
Data Index: 4553433 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.5641. Min Act: -0.1700
Data Index: 7859311 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.5016. Min Act: -0.1700
Data Index: 1398586 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.4391. Min Act: -0.1700
Data Index: 6365185 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.4391. Min Act: -0.1700
Data Index: 6404964 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.4391. Min Act: -0.1700
Data Index: 3208556 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.3766. Min Act: -0.1700
Data Index: 5401666 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.4079. Min Act: -0.1700
Data Index: 4446428 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.3766. Min Act: -0.1700
Data Index: 6185152 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.3454. Min Act: -0.1700
Data Index: 4463453 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.3141. Min Act: -0.1700
Data Index: 6063705 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.3141. Min Act: -0.1700
Data Index: 4945871 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.2829. Min Act: -0.1700
Data Index: 1278312 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.2829. Min Act: -0.1700
Data Index: 5178119 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.2204. Min Act: -0.1700
Data Index: 5521910 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.2516. Min Act: -0.1700
Data Index: 337265 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.2516. Min Act: -0.1700
Data Index: 6404590 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.2516. Min Act: -0.1700
Data Index: 504759 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9391. Min Range: -5.9391
Max Act: 5.2516. Min Act: -0.1700
Data Index: 3436747 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19