Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4642 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2021. Min Range: -7.2021
Max Act: 7.2021. Min Act: -0.1700
Data Index: 4571730 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2021. Min Range: -7.2021
Max Act: 7.0459. Min Act: -0.1700
Data Index: 8465598 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.9834. Min Act: -0.1700
Data Index: 3820400 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.9209. Min Act: -0.1700
Data Index: 2190515 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.8896. Min Act: -0.1700
Data Index: 1083274 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.8896. Min Act: -0.1700
Data Index: 5860164 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.8896. Min Act: -0.1700
Data Index: 2191975 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.8584. Min Act: -0.1700
Data Index: 1563010 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.8271. Min Act: -0.1700
Data Index: 704707 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.8271. Min Act: -0.1700
Data Index: 155469 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.7959. Min Act: -0.1699
Data Index: 7551038 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.7959. Min Act: -0.1700
Data Index: 6946312 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.7959. Min Act: -0.1700
Data Index: 4240795 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.7959. Min Act: -0.1700
Data Index: 7174712 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.7959. Min Act: -0.1700
Data Index: 2509957 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.7959. Min Act: -0.1700
Data Index: 4083818 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.7646. Min Act: -0.1700
Data Index: 2532470 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.7646. Min Act: -0.1700
Data Index: 500939 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.7646. Min Act: -0.1700
Data Index: 6309831 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2021. Min Range: -7.2021
Max Act: 6.7646. Min Act: -0.1700
Data Index: 7835827 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19