Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3340 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3364. Min Range: -7.3364
Max Act: 7.3364. Min Act: -0.1700
Data Index: 600119 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3364. Min Range: -7.3364
Max Act: 7.3364. Min Act: -0.1700
Data Index: 6124481 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3364. Min Range: -7.3364
Max Act: 7.0864. Min Act: -0.1700
Data Index: 8602503 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3364. Min Range: -7.3364
Max Act: 7.0864. Min Act: -0.1700
Data Index: 589999 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.9614. Min Act: -0.1700
Data Index: 8156835 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.9614. Min Act: -0.1700
Data Index: 8095792 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.8364. Min Act: -0.1700
Data Index: 2900276 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.8051. Min Act: -0.1700
Data Index: 846749 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.7739. Min Act: -0.1700
Data Index: 2672720 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.7739. Min Act: -0.1700
Data Index: 6005986 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.7426. Min Act: -0.1700
Data Index: 4778791 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.7114. Min Act: -0.1700
Data Index: 7626961 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.7426. Min Act: -0.1700
Data Index: 200898 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.7114. Min Act: -0.1700
Data Index: 101457 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.6489. Min Act: -0.1700
Data Index: 1911192 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.6176. Min Act: -0.1700
Data Index: 2328159 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.6176. Min Act: -0.1700
Data Index: 7038611 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.5864. Min Act: -0.1700
Data Index: 5463841 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.5864. Min Act: -0.1700
Data Index: 5484186 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3364. Min Range: -7.3364
Max Act: 6.5864. Min Act: -0.1700
Data Index: 5500641 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19