Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1026 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1075. Min Range: -5.1075
Max Act: 5.1075. Min Act: -0.1700
Data Index: 4570166 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.7012. Min Act: -0.1700
Data Index: 7669445 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.6700. Min Act: -0.1700
Data Index: 1891256 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.6700. Min Act: -0.1700
Data Index: 188039 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.6387. Min Act: -0.1700
Data Index: 908903 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.6387. Min Act: -0.1700
Data Index: 6978459 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.5762. Min Act: -0.1700
Data Index: 2705377 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.5762. Min Act: -0.1700
Data Index: 4936228 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.5450. Min Act: -0.1700
Data Index: 2576755 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.5450. Min Act: -0.1700
Data Index: 7922658 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.5137. Min Act: -0.1700
Data Index: 7292554 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.5450. Min Act: -0.1700
Data Index: 806539 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.5450. Min Act: -0.1700
Data Index: 5652434 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.5450. Min Act: -0.1700
Data Index: 6333699 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.5450. Min Act: -0.1700
Data Index: 6272242 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.5137. Min Act: -0.1700
Data Index: 6348210 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.5137. Min Act: -0.1700
Data Index: 1618772 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.4825. Min Act: -0.1700
Data Index: 2982390 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.4825. Min Act: -0.1700
Data Index: 5227641 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1075. Min Range: -5.1075
Max Act: 4.5137. Min Act: -0.1700
Data Index: 2872001 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19