Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2601 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.8605. Min Act: -0.1700
Data Index: 31052 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.7980. Min Act: -0.1700
Data Index: 1233840 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.8293. Min Act: -0.1700
Data Index: 3227070 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.7355. Min Act: -0.1700
Data Index: 7906545 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.7043. Min Act: -0.1700
Data Index: 14363 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.7043. Min Act: -0.1700
Data Index: 8748845 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.6730. Min Act: -0.1700
Data Index: 3415330 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.6105. Min Act: -0.1700
Data Index: 4983705 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.6418. Min Act: -0.1700
Data Index: 1911363 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.5793. Min Act: -0.1700
Data Index: 2701462 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.6105. Min Act: -0.1700
Data Index: 1911365 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.5480. Min Act: -0.1700
Data Index: 1469217 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.5480. Min Act: -0.1700
Data Index: 5347468 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.5480. Min Act: -0.1700
Data Index: 5079152 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.5480. Min Act: -0.1700
Data Index: 8207837 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.5480. Min Act: -0.1700
Data Index: 1756708 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.5168. Min Act: -0.1700
Data Index: 8184226 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.5480. Min Act: -0.1700
Data Index: 1518177 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.4855. Min Act: -0.1700
Data Index: 45762 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8605. Min Range: -5.8605
Max Act: 5.5168. Min Act: -0.1700
Data Index: 3580165 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19