Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2200 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.9194. Min Act: -0.1700
Data Index: 8432118 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.7632. Min Act: -0.1700
Data Index: 8318224 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.3882. Min Act: -0.1700
Data Index: 2101963 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.3257. Min Act: -0.1700
Data Index: 6248706 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.3257. Min Act: -0.1700
Data Index: 5249257 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.2944. Min Act: -0.1700
Data Index: 7836711 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.2632. Min Act: -0.1700
Data Index: 1708256 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.2007. Min Act: -0.1700
Data Index: 6022557 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.1382. Min Act: -0.1700
Data Index: 1341697 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.1069. Min Act: -0.1700
Data Index: 2760151 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.1382. Min Act: -0.1700
Data Index: 2341181 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.1069. Min Act: -0.1700
Data Index: 4405862 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.0757. Min Act: -0.1700
Data Index: 8182051 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.0757. Min Act: -0.1700
Data Index: 1308833 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9194. Min Range: -7.9194
Max Act: 7.0132. Min Act: -0.1700
Data Index: 566462 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9194. Min Range: -7.9194
Max Act: 6.9819. Min Act: -0.1700
Data Index: 5314078 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9194. Min Range: -7.9194
Max Act: 6.9507. Min Act: -0.1700
Data Index: 226580 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9194. Min Range: -7.9194
Max Act: 6.9819. Min Act: -0.1700
Data Index: 370571 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9194. Min Range: -7.9194
Max Act: 6.9819. Min Act: -0.1700
Data Index: 4450476 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9194. Min Range: -7.9194
Max Act: 6.9507. Min Act: -0.1700
Data Index: 5243503 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19