Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 420 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.7352. Min Act: -0.1700
Data Index: 7263040 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.6070. Min Act: -0.1700
Data Index: 4991367 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.6231. Min Act: -0.1700
Data Index: 3058906 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.6070. Min Act: -0.1700
Data Index: 8046236 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.5748. Min Act: -0.1700
Data Index: 551712 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.5748. Min Act: -0.1700
Data Index: 2969064 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.5587. Min Act: -0.1700
Data Index: 6137638 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.5425. Min Act: -0.1700
Data Index: 384185 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.5102. Min Act: -0.1700
Data Index: 5452071 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.4940. Min Act: -0.1700
Data Index: 4756121 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.4940. Min Act: -0.1700
Data Index: 2655864 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.4778. Min Act: -0.1700
Data Index: 7614250 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.4778. Min Act: -0.1700
Data Index: 4668186 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.4940. Min Act: -0.1700
Data Index: 8506692 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.4778. Min Act: -0.1700
Data Index: 138298 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.4615. Min Act: -0.1700
Data Index: 4884964 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.4615. Min Act: -0.1700
Data Index: 3541829 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.4453. Min Act: -0.1700
Data Index: 7794154 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.4290. Min Act: -0.1700
Data Index: 2021691 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7352. Min Range: -2.7352
Max Act: 2.4615. Min Act: -0.1700
Data Index: 254753 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19