Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3818 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.5666. Min Act: -0.1700
Data Index: 5057335 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.4099. Min Act: -0.1700
Data Index: 8417535 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.3315. Min Act: -0.1700
Data Index: 7942656 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.3001. Min Act: -0.1700
Data Index: 4372463 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.2844. Min Act: -0.1700
Data Index: 6034340 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.2530. Min Act: -0.1700
Data Index: 3569112 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.2373. Min Act: -0.1700
Data Index: 5727096 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.2058. Min Act: -0.1700
Data Index: 8401376 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.1901. Min Act: -0.1700
Data Index: 3400090 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.1901. Min Act: -0.1700
Data Index: 4350287 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.1744. Min Act: -0.1700
Data Index: 8078118 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.1429. Min Act: -0.1700
Data Index: 907297 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.1586. Min Act: -0.1700
Data Index: 721219 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.1272. Min Act: -0.1700
Data Index: 5768891 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.1272. Min Act: -0.1700
Data Index: 7511215 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.1114. Min Act: -0.1700
Data Index: 5986272 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.0956. Min Act: -0.1700
Data Index: 4705804 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.0956. Min Act: -0.1700
Data Index: 332576 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.0956. Min Act: -0.1700
Data Index: 4227585 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5666. Min Range: -3.5666
Max Act: 3.0956. Min Act: -0.1700
Data Index: 2848088 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19