Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5461 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3561. Min Range: -7.3561
Max Act: 7.3561. Min Act: -0.1700
Data Index: 6624837 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3561. Min Range: -7.3561
Max Act: 7.3249. Min Act: -0.1700
Data Index: 6667410 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3561. Min Range: -7.3561
Max Act: 7.3249. Min Act: -0.1700
Data Index: 4787992 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3561. Min Range: -7.3561
Max Act: 7.2936. Min Act: -0.1700
Data Index: 841846 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3561. Min Range: -7.3561
Max Act: 7.2936. Min Act: -0.1700
Data Index: 1911856 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3561. Min Range: -7.3561
Max Act: 7.2624. Min Act: -0.1700
Data Index: 1911857 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3561. Min Range: -7.3561
Max Act: 7.2624. Min Act: -0.1700
Data Index: 1911854 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3561. Min Range: -7.3561
Max Act: 7.2624. Min Act: -0.1700
Data Index: 1911855 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3561. Min Range: -7.3561
Max Act: 7.0749. Min Act: -0.1700
Data Index: 5514697 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3561. Min Range: -7.3561
Max Act: 7.0749. Min Act: -0.1700
Data Index: 7946412 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3561. Min Range: -7.3561
Max Act: 7.0436. Min Act: -0.1700
Data Index: 8796441 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3561. Min Range: -7.3561
Max Act: 7.0436. Min Act: -0.1700
Data Index: 1674340 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3561. Min Range: -7.3561
Max Act: 6.9811. Min Act: -0.1700
Data Index: 4830330 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3561. Min Range: -7.3561
Max Act: 6.9499. Min Act: -0.1700
Data Index: 5133918 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3561. Min Range: -7.3561
Max Act: 6.9186. Min Act: -0.1700
Data Index: 2600315 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3561. Min Range: -7.3561
Max Act: 6.8561. Min Act: -0.1700
Data Index: 7932001 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3561. Min Range: -7.3561
Max Act: 6.8561. Min Act: -0.1700
Data Index: 7500556 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3561. Min Range: -7.3561
Max Act: 6.8561. Min Act: -0.1700
Data Index: 5367892 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3561. Min Range: -7.3561
Max Act: 6.8249. Min Act: -0.1700
Data Index: 5356318 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3561. Min Range: -7.3561
Max Act: 6.8249. Min Act: -0.1700
Data Index: 6624838 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19