Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 967 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.8922. Min Act: -0.1700
Data Index: 1347675 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.7047. Min Act: -0.1700
Data Index: 7625738 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.7047. Min Act: -0.1700
Data Index: 1157066 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.6735. Min Act: -0.1700
Data Index: 2107499 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.6110. Min Act: -0.1700
Data Index: 3097898 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.4235. Min Act: -0.1700
Data Index: 33369 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.3922. Min Act: -0.1700
Data Index: 2319148 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.3610. Min Act: -0.1700
Data Index: 7889755 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.3610. Min Act: -0.1700
Data Index: 1807991 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.3610. Min Act: -0.1700
Data Index: 1060724 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.2985. Min Act: -0.1700
Data Index: 1643305 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.2985. Min Act: -0.1700
Data Index: 1523725 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.2672. Min Act: -0.1700
Data Index: 143506 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.2047. Min Act: -0.1700
Data Index: 4088384 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.2672. Min Act: -0.1700
Data Index: 5443328 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.2360. Min Act: -0.1700
Data Index: 6345712 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.2672. Min Act: -0.1700
Data Index: 2896625 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.2047. Min Act: -0.1700
Data Index: 1378887 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.2672. Min Act: -0.1700
Data Index: 737555 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.2360. Min Act: -0.1700
Data Index: 6393754 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19