Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4081 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0554. Min Range: -8.0554
Max Act: 8.0554. Min Act: -0.1700
Data Index: 2627639 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.8992. Min Act: -0.1700
Data Index: 6866496 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.7117. Min Act: -0.1700
Data Index: 2897894 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.6804. Min Act: -0.1700
Data Index: 3443523 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.6179. Min Act: -0.1700
Data Index: 4166148 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.5554. Min Act: -0.1700
Data Index: 699426 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.4929. Min Act: -0.1700
Data Index: 3608565 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.4617. Min Act: -0.1700
Data Index: 5402138 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.4617. Min Act: -0.1700
Data Index: 1603399 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.4304. Min Act: -0.1700
Data Index: 6189868 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.4304. Min Act: -0.1700
Data Index: 2635184 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.4304. Min Act: -0.1700
Data Index: 8444334 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.3679. Min Act: -0.1700
Data Index: 346091 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.3992. Min Act: -0.1700
Data Index: 5817836 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.3679. Min Act: -0.1700
Data Index: 6012074 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.3367. Min Act: -0.1700
Data Index: 6261931 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.2742. Min Act: -0.1700
Data Index: 5788443 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.2742. Min Act: -0.1700
Data Index: 2357717 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.3054. Min Act: -0.1700
Data Index: 7598978 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0554. Min Range: -8.0554
Max Act: 7.2742. Min Act: -0.1700
Data Index: 3014907 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19