Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 947 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.7817. Min Act: -0.1700
Data Index: 7527501 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.6879. Min Act: -0.1700
Data Index: 1912389 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.6879. Min Act: -0.1700
Data Index: 2563697 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.6567. Min Act: -0.1700
Data Index: 5516834 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.6567. Min Act: -0.1700
Data Index: 8823234 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.6254. Min Act: -0.1700
Data Index: 1087744 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.5942. Min Act: -0.1700
Data Index: 7309621 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.5942. Min Act: -0.1700
Data Index: 937989 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.5942. Min Act: -0.1700
Data Index: 1746616 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.5942. Min Act: -0.1700
Data Index: 1351465 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.5629. Min Act: -0.1700
Data Index: 4212706 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.5629. Min Act: -0.1700
Data Index: 1579602 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.5629. Min Act: -0.1700
Data Index: 3748812 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.5629. Min Act: -0.1700
Data Index: 3767871 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.5317. Min Act: -0.1700
Data Index: 8777571 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.5317. Min Act: -0.1700
Data Index: 6289285 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.5004. Min Act: -0.1700
Data Index: 2519529 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.4692. Min Act: -0.1700
Data Index: 7298507 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.4692. Min Act: -0.1700
Data Index: 2980279 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7817. Min Range: -6.7817
Max Act: 6.4379. Min Act: -0.1700
Data Index: 1888648 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19