Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.5202. Min Act: -0.1700
Data Index: 1375492 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.4889. Min Act: -0.1700
Data Index: 8285065 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.3952. Min Act: -0.1700
Data Index: 518321 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.3639. Min Act: -0.1700
Data Index: 3911795 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.3639. Min Act: -0.1700
Data Index: 8474020 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.3327. Min Act: -0.1700
Data Index: 1876881 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.3014. Min Act: -0.1700
Data Index: 3352190 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.2702. Min Act: -0.1700
Data Index: 669798 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.3014. Min Act: -0.1700
Data Index: 3098622 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.3014. Min Act: -0.1700
Data Index: 3379299 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.2702. Min Act: -0.1700
Data Index: 3818383 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.2389. Min Act: -0.1700
Data Index: 891243 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.2702. Min Act: -0.1700
Data Index: 2344933 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.2077. Min Act: -0.1700
Data Index: 5628739 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.2389. Min Act: -0.1700
Data Index: 4494307 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.2077. Min Act: -0.1700
Data Index: 3843265 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.2077. Min Act: -0.1700
Data Index: 832879 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.2077. Min Act: -0.1700
Data Index: 1489857 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.1764. Min Act: -0.1700
Data Index: 5235527 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5202. Min Range: -6.5202
Max Act: 6.1452. Min Act: -0.1700
Data Index: 627165 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19