Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4408 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.8572. Min Act: -0.1700
Data Index: 144283 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.8260. Min Act: -0.1700
Data Index: 5730336 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.7322. Min Act: -0.1700
Data Index: 3400823 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.5760. Min Act: -0.1700
Data Index: 2978948 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.5135. Min Act: -0.1700
Data Index: 2414182 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.4822. Min Act: -0.1700
Data Index: 408188 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.5135. Min Act: -0.1700
Data Index: 7869299 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.4822. Min Act: -0.1700
Data Index: 4711137 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.4510. Min Act: -0.1700
Data Index: 1711290 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.4197. Min Act: -0.1700
Data Index: 5344521 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.4510. Min Act: -0.1700
Data Index: 8183948 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.4822. Min Act: -0.1700
Data Index: 67873 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.4510. Min Act: -0.1700
Data Index: 6275458 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.4510. Min Act: -0.1700
Data Index: 5379401 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.4197. Min Act: -0.1700
Data Index: 7855380 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.4197. Min Act: -0.1700
Data Index: 8802879 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.3885. Min Act: -0.1700
Data Index: 7551155 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.3572. Min Act: -0.1700
Data Index: 1980883 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.4197. Min Act: -0.1700
Data Index: 5969002 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8572. Min Range: -5.8572
Max Act: 5.3572. Min Act: -0.1700
Data Index: 5137393 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19