Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2218 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6398. Min Range: -6.6398
Max Act: 6.6398. Min Act: -0.1700
Data Index: 8159210 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6398. Min Range: -6.6398
Max Act: 6.6086. Min Act: -0.1700
Data Index: 8159211 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6398. Min Range: -6.6398
Max Act: 6.2336. Min Act: -0.1700
Data Index: 109546 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6398. Min Range: -6.6398
Max Act: 6.2023. Min Act: -0.1700
Data Index: 7591458 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.9836. Min Act: -0.1700
Data Index: 469161 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.9836. Min Act: -0.1700
Data Index: 7380775 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.9523. Min Act: -0.1700
Data Index: 3386287 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.9523. Min Act: -0.1700
Data Index: 4907994 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.9211. Min Act: -0.1700
Data Index: 4908000 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.8898. Min Act: -0.1700
Data Index: 4587240 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.8898. Min Act: -0.1700
Data Index: 4838724 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.8586. Min Act: -0.1700
Data Index: 2189487 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.8586. Min Act: -0.1700
Data Index: 4344769 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.8273. Min Act: -0.1700
Data Index: 63355 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.8273. Min Act: -0.1700
Data Index: 7082128 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.7961. Min Act: -0.1700
Data Index: 5123770 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.7961. Min Act: -0.1700
Data Index: 8780135 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.7648. Min Act: -0.1700
Data Index: 4344767 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.7336. Min Act: -0.1700
Data Index: 8664253 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6398. Min Range: -6.6398
Max Act: 5.7336. Min Act: -0.1700
Data Index: 1436849 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19