Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5646 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.8020. Min Act: -0.1700
Data Index: 6912919 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.8020. Min Act: -0.1700
Data Index: 2362517 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.7081. Min Act: -0.1700
Data Index: 7034499 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.6612. Min Act: -0.1700
Data Index: 7034500 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.6612. Min Act: -0.1700
Data Index: 1491260 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.5986. Min Act: -0.1700
Data Index: 262689 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.5986. Min Act: -0.1700
Data Index: 1760434 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.5360. Min Act: -0.1700
Data Index: 6745655 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.4734. Min Act: -0.1700
Data Index: 3117758 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.4890. Min Act: -0.1700
Data Index: 3963274 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.4890. Min Act: -0.1700
Data Index: 3221928 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.4734. Min Act: -0.1700
Data Index: 766279 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.4890. Min Act: -0.1700
Data Index: 8433314 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.4734. Min Act: -0.1700
Data Index: 3890743 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.4734. Min Act: -0.1700
Data Index: 696439 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.4734. Min Act: -0.1700
Data Index: 4669147 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.4734. Min Act: -0.1700
Data Index: 7405354 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.4577. Min Act: -0.1700
Data Index: 1636429 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.4577. Min Act: -0.1700
Data Index: 4594512 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8020. Min Range: -3.8020
Max Act: 3.4263. Min Act: -0.1700
Data Index: 2632932 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19