Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 352 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.9011. Min Act: -0.1700
Data Index: 5212013 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.5261. Min Act: -0.1700
Data Index: 3621167 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.5574. Min Act: -0.1700
Data Index: 5019285 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.2449. Min Act: -0.1700
Data Index: 512528 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.1511. Min Act: -0.1700
Data Index: 3150142 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.1511. Min Act: -0.1700
Data Index: 4083095 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.1511. Min Act: -0.1700
Data Index: 8280829 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.1199. Min Act: -0.1700
Data Index: 5433275 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.1199. Min Act: -0.1700
Data Index: 2602998 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.1199. Min Act: -0.1700
Data Index: 2719316 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.1199. Min Act: -0.1700
Data Index: 1889916 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.0886. Min Act: -0.1700
Data Index: 432116 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.1199. Min Act: -0.1700
Data Index: 4169219 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.0886. Min Act: -0.1700
Data Index: 258047 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.0886. Min Act: -0.1700
Data Index: 3076807 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.0574. Min Act: -0.1700
Data Index: 2875832 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.0574. Min Act: -0.1700
Data Index: 4811328 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.0574. Min Act: -0.1700
Data Index: 822378 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.0574. Min Act: -0.1700
Data Index: 2513752 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9011. Min Range: -5.9011
Max Act: 5.0886. Min Act: -0.1700
Data Index: 1206054 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19