Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2571 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.2792. Min Act: -0.1700
Data Index: 1656460 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.2792. Min Act: -0.1700
Data Index: 3527978 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.2167. Min Act: -0.1700
Data Index: 7623306 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.2167. Min Act: -0.1700
Data Index: 4230157 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.1854. Min Act: -0.1700
Data Index: 4573047 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.1854. Min Act: -0.1700
Data Index: 1685002 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.1229. Min Act: -0.1700
Data Index: 1615474 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.1542. Min Act: -0.1700
Data Index: 3094651 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.1854. Min Act: -0.1700
Data Index: 7771055 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.1229. Min Act: -0.1700
Data Index: 5587186 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.0917. Min Act: -0.1700
Data Index: 5518692 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.1229. Min Act: -0.1700
Data Index: 5700187 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.1229. Min Act: -0.1700
Data Index: 8454629 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.0917. Min Act: -0.1700
Data Index: 5458363 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.0917. Min Act: -0.1700
Data Index: 7515277 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.0604. Min Act: -0.1700
Data Index: 3898982 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.0604. Min Act: -0.1700
Data Index: 3763210 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.0604. Min Act: -0.1700
Data Index: 182117 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.0604. Min Act: -0.1700
Data Index: 5575175 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2792. Min Range: -7.2792
Max Act: 7.0604. Min Act: -0.1700
Data Index: 4545375 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19