Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1527 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.8605. Min Act: -0.1700
Data Index: 2785006 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.8605. Min Act: -0.1700
Data Index: 4594473 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.7355. Min Act: -0.1700
Data Index: 690990 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.7355. Min Act: -0.1700
Data Index: 5596707 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.6730. Min Act: -0.1700
Data Index: 2531210 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.6730. Min Act: -0.1700
Data Index: 2570333 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.6730. Min Act: -0.1700
Data Index: 1246332 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.6730. Min Act: -0.1700
Data Index: 3546718 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.6105. Min Act: -0.1700
Data Index: 4417078 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.6105. Min Act: -0.1700
Data Index: 8538763 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.5480. Min Act: -0.1700
Data Index: 3023281 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.4855. Min Act: -0.1700
Data Index: 4697552 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.4855. Min Act: -0.1700
Data Index: 5309444 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.4855. Min Act: -0.1700
Data Index: 4498478 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.4855. Min Act: -0.1700
Data Index: 6227729 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.4230. Min Act: -0.1700
Data Index: 3569600 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.4230. Min Act: -0.1700
Data Index: 1822381 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.3605. Min Act: -0.1700
Data Index: 8107797 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.3605. Min Act: -0.1700
Data Index: 8229846 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8605. Min Range: -8.8605
Max Act: 8.3605. Min Act: -0.1700
Data Index: 8299240 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19