Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6194 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.8113. Min Act: -0.1700
Data Index: 5919294 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.7488. Min Act: -0.1700
Data Index: 3980200 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.7488. Min Act: -0.1700
Data Index: 5365647 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.6863. Min Act: -0.1700
Data Index: 4426711 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.6238. Min Act: -0.1700
Data Index: 1044420 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.5613. Min Act: -0.1700
Data Index: 2639257 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.5613. Min Act: -0.1700
Data Index: 6041316 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.4988. Min Act: -0.1700
Data Index: 5821216 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.5613. Min Act: -0.1700
Data Index: 8460081 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.4988. Min Act: -0.1700
Data Index: 2634782 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.4988. Min Act: -0.1700
Data Index: 121505 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.4988. Min Act: -0.1700
Data Index: 8213657 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.4363. Min Act: -0.1700
Data Index: 8078112 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.4363. Min Act: -0.1700
Data Index: 638974 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.4363. Min Act: -0.1700
Data Index: 4122880 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.4363. Min Act: -0.1700
Data Index: 6608415 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.3738. Min Act: -0.1700
Data Index: 2237893 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.3738. Min Act: -0.1700
Data Index: 602081 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.3738. Min Act: -0.1700
Data Index: 6958565 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8113. Min Range: -8.8113
Max Act: 8.3738. Min Act: -0.1700
Data Index: 7985347 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19