Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2888 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.9253. Min Act: -0.1700
Data Index: 262382 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.8940. Min Act: -0.1700
Data Index: 2319356 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.9253. Min Act: -0.1700
Data Index: 5001494 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.8628. Min Act: -0.1700
Data Index: 8774676 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.8940. Min Act: -0.1700
Data Index: 4420104 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.8003. Min Act: -0.1700
Data Index: 7339708 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.7690. Min Act: -0.1700
Data Index: 8011584 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.8003. Min Act: -0.1700
Data Index: 6574186 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.7690. Min Act: -0.1700
Data Index: 3301706 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.7690. Min Act: -0.1700
Data Index: 6912717 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.7378. Min Act: -0.1700
Data Index: 1245453 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.7378. Min Act: -0.1700
Data Index: 6764976 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.7065. Min Act: -0.1700
Data Index: 396712 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.7065. Min Act: -0.1700
Data Index: 1433641 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.7065. Min Act: -0.1700
Data Index: 5365626 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.7065. Min Act: -0.1700
Data Index: 7973480 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.6753. Min Act: -0.1700
Data Index: 3701536 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.7065. Min Act: -0.1700
Data Index: 6590431 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.6128. Min Act: -0.1700
Data Index: 7399868 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9253. Min Range: -5.9253
Max Act: 5.6128. Min Act: -0.1700
Data Index: 5573117 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19