Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4285. Min Range: -11.4285
Max Act: 11.4285. Min Act: -0.1700
Data Index: 3949271 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4285. Min Range: -11.4285
Max Act: 11.3660. Min Act: -0.1700
Data Index: 3642460 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4285. Min Range: -11.4285
Max Act: 11.0535. Min Act: -0.1700
Data Index: 8116259 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4285. Min Range: -11.4285
Max Act: 11.0535. Min Act: -0.1700
Data Index: 103977 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.8660. Min Act: -0.1700
Data Index: 683402 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.8660. Min Act: -0.1700
Data Index: 6533768 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.8660. Min Act: -0.1700
Data Index: 4896991 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.8035. Min Act: -0.1700
Data Index: 8488967 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.8035. Min Act: -0.1700
Data Index: 1172100 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.6785. Min Act: -0.1700
Data Index: 4845665 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.7410. Min Act: -0.1700
Data Index: 3254128 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.6785. Min Act: -0.1700
Data Index: 4468290 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.5535. Min Act: -0.1700
Data Index: 1172715 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.4910. Min Act: -0.1700
Data Index: 2371838 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.4910. Min Act: -0.1700
Data Index: 898953 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.4910. Min Act: -0.1700
Data Index: 2148237 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.3660. Min Act: -0.1700
Data Index: 2026432 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.3660. Min Act: -0.1700
Data Index: 3540949 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.3660. Min Act: -0.1700
Data Index: 6699139 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4285. Min Range: -11.4285
Max Act: 10.3035. Min Act: -0.1700
Data Index: 5180332 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19