Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4044 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.6276. Min Act: -0.1700
Data Index: 1500757 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.3776. Min Act: -0.1700
Data Index: 5143687 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.4088. Min Act: -0.1700
Data Index: 196865 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.3151. Min Act: -0.1700
Data Index: 7880071 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.2838. Min Act: -0.1700
Data Index: 8304284 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.2838. Min Act: -0.1700
Data Index: 8747712 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.2838. Min Act: -0.1700
Data Index: 7460228 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.2526. Min Act: -0.1700
Data Index: 847271 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.2526. Min Act: -0.1700
Data Index: 8216188 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.2526. Min Act: -0.1700
Data Index: 3065052 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.1276. Min Act: -0.1700
Data Index: 3971707 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.0651. Min Act: -0.1700
Data Index: 515665 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.0963. Min Act: -0.1700
Data Index: 3866163 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.0338. Min Act: -0.1700
Data Index: 4249102 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.0651. Min Act: -0.1700
Data Index: 8105402 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.0651. Min Act: -0.1700
Data Index: 4391719 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.0651. Min Act: -0.1700
Data Index: 4425140 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.0338. Min Act: -0.1700
Data Index: 1811909 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.0026. Min Act: -0.1700
Data Index: 8227144 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6276. Min Range: -7.6276
Max Act: 7.0026. Min Act: -0.1700
Data Index: 5252343 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19