Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.6783. Min Act: -0.1700
Data Index: 817784 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.6158. Min Act: -0.1700
Data Index: 6878358 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.5845. Min Act: -0.1700
Data Index: 1976326 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.5533. Min Act: -0.1700
Data Index: 3525698 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.5220. Min Act: -0.1700
Data Index: 791039 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.4908. Min Act: -0.1700
Data Index: 817783 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.4908. Min Act: -0.1700
Data Index: 6075192 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.4595. Min Act: -0.1700
Data Index: 2324017 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.4283. Min Act: -0.1700
Data Index: 864837 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.3970. Min Act: -0.1700
Data Index: 5736690 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.3658. Min Act: -0.1700
Data Index: 8355920 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.3970. Min Act: -0.1700
Data Index: 4186222 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.3970. Min Act: -0.1700
Data Index: 4293984 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.3658. Min Act: -0.1700
Data Index: 1737566 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.3658. Min Act: -0.1700
Data Index: 1203322 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.3658. Min Act: -0.1700
Data Index: 8038983 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.3345. Min Act: -0.1700
Data Index: 6053383 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.3345. Min Act: -0.1700
Data Index: 3213395 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.3345. Min Act: -0.1700
Data Index: 6092996 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6783. Min Range: -4.6783
Max Act: 4.3345. Min Act: -0.1700
Data Index: 2080108 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19