Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2164 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0220. Min Range: -6.0220
Max Act: 6.0220. Min Act: -0.1700
Data Index: 5554503 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.8345. Min Act: -0.1700
Data Index: 7817711 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.7408. Min Act: -0.1700
Data Index: 857014 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.6783. Min Act: -0.1700
Data Index: 2698349 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.6470. Min Act: -0.1700
Data Index: 710152 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.6470. Min Act: -0.1700
Data Index: 1602019 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.5533. Min Act: -0.1700
Data Index: 720011 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.5845. Min Act: -0.1700
Data Index: 7886804 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.5845. Min Act: -0.1700
Data Index: 3142866 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.5845. Min Act: -0.1700
Data Index: 7601109 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.5533. Min Act: -0.1700
Data Index: 2552193 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.5220. Min Act: -0.1700
Data Index: 2600037 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.5533. Min Act: -0.1700
Data Index: 7461443 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.5533. Min Act: -0.1700
Data Index: 5157098 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.5220. Min Act: -0.1700
Data Index: 5413602 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.5220. Min Act: -0.1700
Data Index: 2985642 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.5220. Min Act: -0.1700
Data Index: 2207835 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.4908. Min Act: -0.1700
Data Index: 3262509 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.5220. Min Act: -0.1700
Data Index: 2419651 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0220. Min Range: -6.0220
Max Act: 5.5220. Min Act: -0.1700
Data Index: 8015282 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19