Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1802 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3277. Min Range: -6.3277
Max Act: 6.3277. Min Act: -0.1700
Data Index: 5837632 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3277. Min Range: -6.3277
Max Act: 6.1714. Min Act: -0.1700
Data Index: 7667500 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3277. Min Range: -6.3277
Max Act: 6.1402. Min Act: -0.1700
Data Index: 5490767 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3277. Min Range: -6.3277
Max Act: 6.1402. Min Act: -0.1700
Data Index: 4708523 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3277. Min Range: -6.3277
Max Act: 6.1089. Min Act: -0.1700
Data Index: 14635 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3277. Min Range: -6.3277
Max Act: 6.0777. Min Act: -0.1700
Data Index: 522744 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3277. Min Range: -6.3277
Max Act: 6.0777. Min Act: -0.1700
Data Index: 1392389 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3277. Min Range: -6.3277
Max Act: 6.0777. Min Act: -0.1700
Data Index: 2125386 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3277. Min Range: -6.3277
Max Act: 6.0152. Min Act: -0.1700
Data Index: 4061513 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3277. Min Range: -6.3277
Max Act: 6.0152. Min Act: -0.1700
Data Index: 212834 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3277. Min Range: -6.3277
Max Act: 6.0152. Min Act: -0.1700
Data Index: 5995361 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3277. Min Range: -6.3277
Max Act: 5.9839. Min Act: -0.1700
Data Index: 2527658 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3277. Min Range: -6.3277
Max Act: 5.9839. Min Act: -0.1700
Data Index: 6456956 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3277. Min Range: -6.3277
Max Act: 5.9527. Min Act: -0.1700
Data Index: 4041769 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3277. Min Range: -6.3277
Max Act: 5.9527. Min Act: -0.1700
Data Index: 5490580 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3277. Min Range: -6.3277
Max Act: 5.9527. Min Act: -0.1700
Data Index: 5078399 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3277. Min Range: -6.3277
Max Act: 5.9527. Min Act: -0.1700
Data Index: 269136 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3277. Min Range: -6.3277
Max Act: 5.9214. Min Act: -0.1700
Data Index: 688578 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3277. Min Range: -6.3277
Max Act: 5.8902. Min Act: -0.1700
Data Index: 3475342 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3277. Min Range: -6.3277
Max Act: 5.9214. Min Act: -0.1700
Data Index: 4456728 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19