Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1826 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4283. Min Range: -6.4283
Max Act: 6.4283. Min Act: -0.1700
Data Index: 97207 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.9908. Min Act: -0.1700
Data Index: 133014 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.9595. Min Act: -0.1700
Data Index: 5777467 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.8033. Min Act: -0.1700
Data Index: 55915 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.7720. Min Act: -0.1700
Data Index: 6280636 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.7408. Min Act: -0.1700
Data Index: 1486471 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.7408. Min Act: -0.1700
Data Index: 4260481 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.7408. Min Act: -0.1700
Data Index: 38438 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.7408. Min Act: -0.1700
Data Index: 8312649 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.7095. Min Act: -0.1700
Data Index: 1784397 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.6470. Min Act: -0.1700
Data Index: 2319528 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.6158. Min Act: -0.1700
Data Index: 3696031 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.6158. Min Act: -0.1700
Data Index: 8074779 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.5533. Min Act: -0.1700
Data Index: 4819690 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.5220. Min Act: -0.1700
Data Index: 6764092 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.5220. Min Act: -0.1700
Data Index: 8050578 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.4595. Min Act: -0.1700
Data Index: 1245442 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.4595. Min Act: -0.1700
Data Index: 342330 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.4595. Min Act: -0.1700
Data Index: 8077101 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4283. Min Range: -6.4283
Max Act: 5.4595. Min Act: -0.1700
Data Index: 1013841 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19