Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5720 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4168. Min Range: -6.4168
Max Act: 6.4168. Min Act: -0.1700
Data Index: 539252 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4168. Min Range: -6.4168
Max Act: 6.3855. Min Act: -0.1700
Data Index: 6549580 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4168. Min Range: -6.4168
Max Act: 6.2918. Min Act: -0.1700
Data Index: 3839931 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4168. Min Range: -6.4168
Max Act: 6.0730. Min Act: -0.1700
Data Index: 1600612 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4168. Min Range: -6.4168
Max Act: 6.0105. Min Act: -0.1700
Data Index: 865626 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.9480. Min Act: -0.1700
Data Index: 4067550 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.9168. Min Act: -0.1700
Data Index: 8401350 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.8855. Min Act: -0.1700
Data Index: 7935328 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.8855. Min Act: -0.1700
Data Index: 5252022 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.8855. Min Act: -0.1700
Data Index: 7060149 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.8543. Min Act: -0.1700
Data Index: 7557897 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.8543. Min Act: -0.1700
Data Index: 2021545 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.8543. Min Act: -0.1700
Data Index: 6537683 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.8230. Min Act: -0.1700
Data Index: 1875025 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.8230. Min Act: -0.1700
Data Index: 2081394 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.8230. Min Act: -0.1700
Data Index: 5737630 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.7918. Min Act: -0.1700
Data Index: 1364001 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.7918. Min Act: -0.1700
Data Index: 794863 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.7918. Min Act: -0.1700
Data Index: 7324527 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4168. Min Range: -6.4168
Max Act: 5.7605. Min Act: -0.1700
Data Index: 3032749 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19