Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6140 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.4837. Min Act: -0.1700
Data Index: 6145444 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.4524. Min Act: -0.1700
Data Index: 8060271 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.4212. Min Act: -0.1700
Data Index: 4601422 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.2649. Min Act: -0.1700
Data Index: 2257775 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.2962. Min Act: -0.1700
Data Index: 6378943 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.2337. Min Act: -0.1700
Data Index: 1275102 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.2024. Min Act: -0.1700
Data Index: 1989531 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.1712. Min Act: -0.1700
Data Index: 260537 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.1399. Min Act: -0.1700
Data Index: 6694894 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.1087. Min Act: -0.1700
Data Index: 5952739 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.1087. Min Act: -0.1700
Data Index: 2505876 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.0774. Min Act: -0.1700
Data Index: 3760021 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.0774. Min Act: -0.1700
Data Index: 8352739 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.0774. Min Act: -0.1700
Data Index: 6095647 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.0462. Min Act: -0.1700
Data Index: 1757468 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.0462. Min Act: -0.1700
Data Index: 6122092 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4837. Min Range: -7.4837
Max Act: 7.0149. Min Act: -0.1700
Data Index: 5490236 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4837. Min Range: -7.4837
Max Act: 6.9837. Min Act: -0.1700
Data Index: 4304216 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4837. Min Range: -7.4837
Max Act: 6.9837. Min Act: -0.1700
Data Index: 4557942 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4837. Min Range: -7.4837
Max Act: 6.9837. Min Act: -0.1700
Data Index: 5419290 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19