Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.7790. Min Act: -0.1700
Data Index: 3610076 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.7165. Min Act: -0.1700
Data Index: 6592898 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.5602. Min Act: -0.1700
Data Index: 2291158 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.4977. Min Act: -0.1700
Data Index: 7457214 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.4977. Min Act: -0.1700
Data Index: 6653580 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.4665. Min Act: -0.1700
Data Index: 5027821 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.4665. Min Act: -0.1700
Data Index: 6186226 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.4352. Min Act: -0.1700
Data Index: 7265539 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.4040. Min Act: -0.1700
Data Index: 2353703 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.3727. Min Act: -0.1700
Data Index: 8645619 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.3727. Min Act: -0.1700
Data Index: 8684088 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.3727. Min Act: -0.1700
Data Index: 2874692 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.3102. Min Act: -0.1700
Data Index: 4400449 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.3102. Min Act: -0.1700
Data Index: 3075130 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.3102. Min Act: -0.1700
Data Index: 5646813 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.3102. Min Act: -0.1700
Data Index: 6020580 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.2790. Min Act: -0.1700
Data Index: 1430783 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.2477. Min Act: -0.1700
Data Index: 6612470 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.2477. Min Act: -0.1700
Data Index: 2245239 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7790. Min Range: -5.7790
Max Act: 5.2477. Min Act: -0.1700
Data Index: 6922153 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19