Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1517 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.3648. Min Act: -0.1700
Data Index: 7803932 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.2710. Min Act: -0.1700
Data Index: 5936006 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.2398. Min Act: -0.1700
Data Index: 7228234 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.2085. Min Act: -0.1700
Data Index: 4252951 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.1148. Min Act: -0.1700
Data Index: 2427900 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.1148. Min Act: -0.1700
Data Index: 8548773 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.1148. Min Act: -0.1700
Data Index: 4732252 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.1148. Min Act: -0.1700
Data Index: 7324077 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.1148. Min Act: -0.1700
Data Index: 7496044 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.0835. Min Act: -0.1700
Data Index: 4863349 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.0835. Min Act: -0.1700
Data Index: 5069879 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.0835. Min Act: -0.1700
Data Index: 7655216 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.0523. Min Act: -0.1700
Data Index: 2099871 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.0523. Min Act: -0.1700
Data Index: 666438 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.0523. Min Act: -0.1700
Data Index: 1375617 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.0523. Min Act: -0.1700
Data Index: 2055119 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.0523. Min Act: -0.1700
Data Index: 4863348 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.0523. Min Act: -0.1700
Data Index: 6471721 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.0210. Min Act: -0.1700
Data Index: 1801317 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3648. Min Range: -6.3648
Max Act: 6.0210. Min Act: -0.1700
Data Index: 2721114 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19