Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4423 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9400. Min Range: -8.9400
Max Act: 8.9400. Min Act: -0.1700
Data Index: 5009670 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9400. Min Range: -8.9400
Max Act: 8.3775. Min Act: -0.1700
Data Index: 2684965 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9400. Min Range: -8.9400
Max Act: 8.2525. Min Act: -0.1700
Data Index: 2372708 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9400. Min Range: -8.9400
Max Act: 8.2525. Min Act: -0.1700
Data Index: 695223 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9400. Min Range: -8.9400
Max Act: 8.2525. Min Act: -0.1700
Data Index: 1043601 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9400. Min Range: -8.9400
Max Act: 8.1900. Min Act: -0.1700
Data Index: 424095 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9400. Min Range: -8.9400
Max Act: 8.1275. Min Act: -0.1700
Data Index: 1641200 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9400. Min Range: -8.9400
Max Act: 8.0650. Min Act: -0.1700
Data Index: 8579329 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9400. Min Range: -8.9400
Max Act: 8.0650. Min Act: -0.1700
Data Index: 7630280 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9400. Min Range: -8.9400
Max Act: 8.0025. Min Act: -0.1700
Data Index: 1444143 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9400. Min Range: -8.9400
Max Act: 8.0025. Min Act: -0.1700
Data Index: 8028174 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9400. Min Range: -8.9400
Max Act: 8.0025. Min Act: -0.1700
Data Index: 717218 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9400. Min Range: -8.9400
Max Act: 7.9400. Min Act: -0.1700
Data Index: 5181440 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9400. Min Range: -8.9400
Max Act: 7.9400. Min Act: -0.1700
Data Index: 1109071 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9400. Min Range: -8.9400
Max Act: 7.9400. Min Act: -0.1700
Data Index: 6249784 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9400. Min Range: -8.9400
Max Act: 8.0025. Min Act: -0.1700
Data Index: 2191725 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9400. Min Range: -8.9400
Max Act: 7.9400. Min Act: -0.1700
Data Index: 791217 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9400. Min Range: -8.9400
Max Act: 7.9400. Min Act: -0.1700
Data Index: 5054331 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9400. Min Range: -8.9400
Max Act: 7.9400. Min Act: -0.1700
Data Index: 5945694 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9400. Min Range: -8.9400
Max Act: 7.8775. Min Act: -0.1700
Data Index: 4313655 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19