Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4789 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2180. Min Range: -6.2180
Max Act: 6.2180. Min Act: -0.1700
Data Index: 7186603 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2180. Min Range: -6.2180
Max Act: 6.2180. Min Act: -0.1700
Data Index: 1191959 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2180. Min Range: -6.2180
Max Act: 6.1868. Min Act: -0.1700
Data Index: 8767535 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2180. Min Range: -6.2180
Max Act: 6.1555. Min Act: -0.1700
Data Index: 7402217 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2180. Min Range: -6.2180
Max Act: 6.1555. Min Act: -0.1700
Data Index: 2340423 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2180. Min Range: -6.2180
Max Act: 6.0305. Min Act: -0.1700
Data Index: 3146821 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2180. Min Range: -6.2180
Max Act: 6.0305. Min Act: -0.1700
Data Index: 3870093 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2180. Min Range: -6.2180
Max Act: 6.0305. Min Act: -0.1700
Data Index: 6905439 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2180. Min Range: -6.2180
Max Act: 5.9993. Min Act: -0.1700
Data Index: 4488270 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2180. Min Range: -6.2180
Max Act: 5.9680. Min Act: -0.1700
Data Index: 5671399 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2180. Min Range: -6.2180
Max Act: 5.9368. Min Act: -0.1700
Data Index: 6959155 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2180. Min Range: -6.2180
Max Act: 5.9055. Min Act: -0.1700
Data Index: 4748891 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2180. Min Range: -6.2180
Max Act: 5.9055. Min Act: -0.1700
Data Index: 2839596 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2180. Min Range: -6.2180
Max Act: 5.9055. Min Act: -0.1700
Data Index: 8759206 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2180. Min Range: -6.2180
Max Act: 5.9055. Min Act: -0.1700
Data Index: 1333488 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2180. Min Range: -6.2180
Max Act: 5.8743. Min Act: -0.1700
Data Index: 1672506 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2180. Min Range: -6.2180
Max Act: 5.8743. Min Act: -0.1700
Data Index: 178028 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2180. Min Range: -6.2180
Max Act: 5.9055. Min Act: -0.1700
Data Index: 8518235 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2180. Min Range: -6.2180
Max Act: 5.8430. Min Act: -0.1700
Data Index: 6440303 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2180. Min Range: -6.2180
Max Act: 5.8430. Min Act: -0.1700
Data Index: 37458 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19