Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2875 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.8674. Min Act: -0.1700
Data Index: 1645209 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.6174. Min Act: -0.1700
Data Index: 6824422 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.5862. Min Act: -0.1700
Data Index: 270205 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.5862. Min Act: -0.1700
Data Index: 5310742 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.5862. Min Act: -0.1700
Data Index: 3458544 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.4924. Min Act: -0.1700
Data Index: 5445041 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.5237. Min Act: -0.1700
Data Index: 5976693 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.4924. Min Act: -0.1700
Data Index: 1933463 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.4612. Min Act: -0.1700
Data Index: 38235 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.3674. Min Act: -0.1700
Data Index: 753295 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.3362. Min Act: -0.1700
Data Index: 5696117 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.3362. Min Act: -0.1700
Data Index: 3794602 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.3362. Min Act: -0.1700
Data Index: 8196555 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.3049. Min Act: -0.1700
Data Index: 2838347 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.2737. Min Act: -0.1700
Data Index: 2429624 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.2424. Min Act: -0.1700
Data Index: 165099 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.2112. Min Act: -0.1700
Data Index: 1009331 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.2424. Min Act: -0.1700
Data Index: 6989991 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.2424. Min Act: -0.1700
Data Index: 6494583 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.2424. Min Act: -0.1700
Data Index: 3924832 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19