Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1111 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0259. Min Range: -7.0259
Max Act: 7.0259. Min Act: -0.1700
Data Index: 3986285 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.8071. Min Act: -0.1700
Data Index: 598329 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.7446. Min Act: -0.1700
Data Index: 7266656 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.6821. Min Act: -0.1700
Data Index: 7007543 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.6509. Min Act: -0.1700
Data Index: 5280858 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.6196. Min Act: -0.1700
Data Index: 4392705 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.5884. Min Act: -0.1700
Data Index: 2193267 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.6196. Min Act: -0.1700
Data Index: 787410 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.5884. Min Act: -0.1700
Data Index: 51868 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.4321. Min Act: -0.1700
Data Index: 7255351 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.4009. Min Act: -0.1700
Data Index: 4967774 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.3696. Min Act: -0.1700
Data Index: 1931208 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.4009. Min Act: -0.1700
Data Index: 5105963 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.3071. Min Act: -0.1700
Data Index: 954523 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.3384. Min Act: -0.1700
Data Index: 532039 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.3384. Min Act: -0.1700
Data Index: 1660816 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.3384. Min Act: -0.1700
Data Index: 3611747 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.3071. Min Act: -0.1700
Data Index: 6883228 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.2759. Min Act: -0.1700
Data Index: 6249912 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0259. Min Range: -7.0259
Max Act: 6.2759. Min Act: -0.1700
Data Index: 525668 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19