Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3025 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1789. Min Range: -6.1789
Max Act: 6.1789. Min Act: -0.1700
Data Index: 480571 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1789. Min Range: -6.1789
Max Act: 6.1477. Min Act: -0.1700
Data Index: 261211 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1789. Min Range: -6.1789
Max Act: 6.0539. Min Act: -0.1700
Data Index: 4469490 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1789. Min Range: -6.1789
Max Act: 6.0227. Min Act: -0.1700
Data Index: 5718381 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.9602. Min Act: -0.1700
Data Index: 4468082 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.9602. Min Act: -0.1700
Data Index: 5035958 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.9289. Min Act: -0.1700
Data Index: 6349906 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.9289. Min Act: -0.1700
Data Index: 4204738 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.9289. Min Act: -0.1700
Data Index: 5191950 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.9289. Min Act: -0.1700
Data Index: 8362554 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.9289. Min Act: -0.1700
Data Index: 5739374 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.8977. Min Act: -0.1700
Data Index: 573450 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.8664. Min Act: -0.1700
Data Index: 1704513 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.8352. Min Act: -0.1700
Data Index: 2353102 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.8664. Min Act: -0.1700
Data Index: 4215851 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.8664. Min Act: -0.1700
Data Index: 2220015 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.8664. Min Act: -0.1700
Data Index: 25115 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.8352. Min Act: -0.1700
Data Index: 880025 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.8039. Min Act: -0.1700
Data Index: 2911647 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1789. Min Range: -6.1789
Max Act: 5.8352. Min Act: -0.1700
Data Index: 6055828 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19