Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5813 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.6181. Min Act: -0.1700
Data Index: 8587053 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.4618. Min Act: -0.1700
Data Index: 3260973 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.3993. Min Act: -0.1700
Data Index: 2193387 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.3993. Min Act: -0.1700
Data Index: 5190651 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.3681. Min Act: -0.1700
Data Index: 7608135 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.3681. Min Act: -0.1700
Data Index: 7136096 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.3993. Min Act: -0.1700
Data Index: 2714652 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.3368. Min Act: -0.1700
Data Index: 4437599 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.3681. Min Act: -0.1700
Data Index: 3171393 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.3368. Min Act: -0.1700
Data Index: 6248786 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.3368. Min Act: -0.1700
Data Index: 1060406 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.3368. Min Act: -0.1700
Data Index: 5073755 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.3368. Min Act: -0.1700
Data Index: 1012083 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.3056. Min Act: -0.1700
Data Index: 699924 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.2743. Min Act: -0.1700
Data Index: 4744316 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.2743. Min Act: -0.1700
Data Index: 6999688 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.2431. Min Act: -0.1700
Data Index: 6802240 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.2118. Min Act: -0.1700
Data Index: 2499311 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.2118. Min Act: -0.1700
Data Index: 7422910 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6181. Min Range: -5.6181
Max Act: 5.2118. Min Act: -0.1700
Data Index: 2216687 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19