Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5058 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.7018. Min Range: -11.7018
Max Act: 11.7018. Min Act: -0.1700
Data Index: 678784 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.7018. Min Range: -11.7018
Max Act: 11.6393. Min Act: -0.1700
Data Index: 197364 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.7018. Min Range: -11.7018
Max Act: 11.5143. Min Act: -0.1700
Data Index: 5281335 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.7018. Min Range: -11.7018
Max Act: 11.4518. Min Act: -0.1700
Data Index: 4963767 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.7018. Min Range: -11.7018
Max Act: 11.4518. Min Act: -0.1700
Data Index: 4524975 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.7018. Min Range: -11.7018
Max Act: 11.3268. Min Act: -0.1700
Data Index: 6538840 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.7018. Min Range: -11.7018
Max Act: 11.1393. Min Act: -0.1700
Data Index: 6541604 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.7018. Min Range: -11.7018
Max Act: 11.0143. Min Act: -0.1700
Data Index: 1025037 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.7018. Min Range: -11.7018
Max Act: 10.8893. Min Act: -0.1700
Data Index: 146158 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.7018. Min Range: -11.7018
Max Act: 10.8893. Min Act: -0.1700
Data Index: 7997467 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.7018. Min Range: -11.7018
Max Act: 10.8268. Min Act: -0.1700
Data Index: 3873801 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.7018. Min Range: -11.7018
Max Act: 10.8893. Min Act: -0.1700
Data Index: 5333692 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.7018. Min Range: -11.7018
Max Act: 10.8893. Min Act: -0.1700
Data Index: 1152405 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.7018. Min Range: -11.7018
Max Act: 10.8268. Min Act: -0.1700
Data Index: 3231182 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.7018. Min Range: -11.7018
Max Act: 10.7643. Min Act: -0.1700
Data Index: 8438172 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.7018. Min Range: -11.7018
Max Act: 10.7643. Min Act: -0.1700
Data Index: 3644770 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.7018. Min Range: -11.7018
Max Act: 10.7643. Min Act: -0.1700
Data Index: 4800222 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.7018. Min Range: -11.7018
Max Act: 10.7643. Min Act: -0.1700
Data Index: 8694946 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.7018. Min Range: -11.7018
Max Act: 10.7643. Min Act: -0.1700
Data Index: 2471799 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.7018. Min Range: -11.7018
Max Act: 10.7018. Min Act: -0.1700
Data Index: 3901083 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19