Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3980. Min Range: -6.3980
Max Act: 6.3980. Min Act: -0.1700
Data Index: 3570856 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.5542. Min Act: -0.1700
Data Index: 3564948 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.5230. Min Act: -0.1700
Data Index: 7080437 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.5230. Min Act: -0.1700
Data Index: 2657932 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.4605. Min Act: -0.1700
Data Index: 2217262 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.4917. Min Act: -0.1700
Data Index: 1906946 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.4605. Min Act: -0.1700
Data Index: 170420 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.4605. Min Act: -0.1700
Data Index: 3420554 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.3980. Min Act: -0.1700
Data Index: 3001093 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.4292. Min Act: -0.1700
Data Index: 5307427 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.4292. Min Act: -0.1700
Data Index: 6542590 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.3980. Min Act: -0.1700
Data Index: 2908280 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.3980. Min Act: -0.1700
Data Index: 4569251 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.3667. Min Act: -0.1700
Data Index: 677120 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.3667. Min Act: -0.1700
Data Index: 5863850 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.3667. Min Act: -0.1700
Data Index: 2482424 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.3667. Min Act: -0.1700
Data Index: 371797 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.3355. Min Act: -0.1700
Data Index: 1441751 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.3355. Min Act: -0.1700
Data Index: 3023145 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.3667. Min Act: -0.1700
Data Index: 5204950 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19