Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1025 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.4156. Min Act: -0.1700
Data Index: 8497578 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.3058. Min Act: -0.1700
Data Index: 2658376 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.2901. Min Act: -0.1700
Data Index: 1976704 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.2744. Min Act: -0.1700
Data Index: 3997948 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.2901. Min Act: -0.1700
Data Index: 5023190 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.2430. Min Act: -0.1700
Data Index: 2382924 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1958. Min Act: -0.1700
Data Index: 2666894 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1958. Min Act: -0.1700
Data Index: 4073003 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1801. Min Act: -0.1700
Data Index: 5732512 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1801. Min Act: -0.1700
Data Index: 4418341 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1643. Min Act: -0.1700
Data Index: 1712801 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1486. Min Act: -0.1700
Data Index: 7380694 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1486. Min Act: -0.1700
Data Index: 7619448 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1329. Min Act: -0.1700
Data Index: 8155733 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1486. Min Act: -0.1700
Data Index: 8421927 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1486. Min Act: -0.1700
Data Index: 5558737 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1643. Min Act: -0.1700
Data Index: 4125332 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1486. Min Act: -0.1700
Data Index: 1364739 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1486. Min Act: -0.1700
Data Index: 8047351 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4156. Min Range: -3.4156
Max Act: 3.1171. Min Act: -0.1700
Data Index: 1277974 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19