Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0660. Min Range: -5.0660
Max Act: 5.0660. Min Act: -0.1700
Data Index: 2518957 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.9410. Min Act: -0.1700
Data Index: 7260805 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.9410. Min Act: -0.1700
Data Index: 7176689 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.8472. Min Act: -0.1700
Data Index: 18435 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.8160. Min Act: -0.1700
Data Index: 3093715 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.8160. Min Act: -0.1700
Data Index: 3389405 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.7847. Min Act: -0.1700
Data Index: 4182771 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.7535. Min Act: -0.1700
Data Index: 8729682 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.7847. Min Act: -0.1700
Data Index: 3579610 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.7535. Min Act: -0.1700
Data Index: 7427317 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.7535. Min Act: -0.1700
Data Index: 207084 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.7535. Min Act: -0.1700
Data Index: 5778193 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.7222. Min Act: -0.1700
Data Index: 4568722 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.7222. Min Act: -0.1700
Data Index: 3537679 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.7222. Min Act: -0.1700
Data Index: 6969206 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.7222. Min Act: -0.1700
Data Index: 8305981 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.6597. Min Act: -0.1700
Data Index: 5315351 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.6597. Min Act: -0.1700
Data Index: 1842549 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.6285. Min Act: -0.1700
Data Index: 7054652 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0660. Min Range: -5.0660
Max Act: 4.6285. Min Act: -0.1700
Data Index: 2690934 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19