Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3393 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1283. Min Range: -8.1283
Max Act: 8.1283. Min Act: -0.1700
Data Index: 7624827 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.9408. Min Act: -0.1700
Data Index: 1529826 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.9408. Min Act: -0.1700
Data Index: 5075148 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.7533. Min Act: -0.1700
Data Index: 5710861 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.6595. Min Act: -0.1700
Data Index: 4708663 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.6283. Min Act: -0.1700
Data Index: 5337814 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.5658. Min Act: -0.1700
Data Index: 2188691 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.5658. Min Act: -0.1700
Data Index: 2221581 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.5345. Min Act: -0.1700
Data Index: 3620701 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.5033. Min Act: -0.1700
Data Index: 2614815 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.4408. Min Act: -0.1700
Data Index: 89305 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.3470. Min Act: -0.1700
Data Index: 4406843 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.3783. Min Act: -0.1700
Data Index: 8541537 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.3470. Min Act: -0.1700
Data Index: 1505219 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.3470. Min Act: -0.1700
Data Index: 5541964 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.3158. Min Act: -0.1700
Data Index: 3836155 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.3158. Min Act: -0.1700
Data Index: 1244980 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.2845. Min Act: -0.1700
Data Index: 5357405 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.2533. Min Act: -0.1700
Data Index: 7466054 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1283. Min Range: -8.1283
Max Act: 7.2220. Min Act: -0.1700
Data Index: 2455695 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19