Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 971 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0254. Min Range: -7.0254
Max Act: 7.0254. Min Act: -0.1700
Data Index: 4691290 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.9629. Min Act: -0.1700
Data Index: 601438 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.8066. Min Act: -0.1700
Data Index: 5788243 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.7441. Min Act: -0.1700
Data Index: 2616368 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.6816. Min Act: -0.1700
Data Index: 174963 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.6816. Min Act: -0.1700
Data Index: 8030662 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.6816. Min Act: -0.1700
Data Index: 4376182 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.6504. Min Act: -0.1700
Data Index: 2536388 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.6504. Min Act: -0.1700
Data Index: 1432916 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.6504. Min Act: -0.1700
Data Index: 4892973 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.5879. Min Act: -0.1700
Data Index: 3131517 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.6191. Min Act: -0.1700
Data Index: 2032888 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.5879. Min Act: -0.1700
Data Index: 4881188 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.5566. Min Act: -0.1700
Data Index: 1827488 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.6191. Min Act: -0.1700
Data Index: 475788 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.5566. Min Act: -0.1700
Data Index: 7867787 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.5566. Min Act: -0.1700
Data Index: 6988583 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.5566. Min Act: -0.1700
Data Index: 6426145 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.5254. Min Act: -0.1700
Data Index: 4617642 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0254. Min Range: -7.0254
Max Act: 6.5254. Min Act: -0.1700
Data Index: 5694649 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19