Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.6169. Min Act: -0.1700
Data Index: 8244495 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.3981. Min Act: -0.1700
Data Index: 7903239 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.3981. Min Act: -0.1700
Data Index: 194641 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.1794. Min Act: -0.1700
Data Index: 4105731 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.2106. Min Act: -0.1700
Data Index: 2251874 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.2106. Min Act: -0.1700
Data Index: 626346 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.1481. Min Act: -0.1700
Data Index: 5128261 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.1169. Min Act: -0.1700
Data Index: 3868578 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.1169. Min Act: -0.1700
Data Index: 5181158 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.0856. Min Act: -0.1700
Data Index: 2480529 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.0544. Min Act: -0.1700
Data Index: 1746199 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.0231. Min Act: -0.1700
Data Index: 4368958 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.0231. Min Act: -0.1700
Data Index: 8321596 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6169. Min Range: -6.6169
Max Act: 5.9919. Min Act: -0.1700
Data Index: 4891655 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6169. Min Range: -6.6169
Max Act: 5.9919. Min Act: -0.1700
Data Index: 4295648 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6169. Min Range: -6.6169
Max Act: 5.9606. Min Act: -0.1700
Data Index: 1019199 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6169. Min Range: -6.6169
Max Act: 5.9606. Min Act: -0.1700
Data Index: 3917653 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6169. Min Range: -6.6169
Max Act: 5.9294. Min Act: -0.1700
Data Index: 3100947 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6169. Min Range: -6.6169
Max Act: 5.9294. Min Act: -0.1700
Data Index: 2367207 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6169. Min Range: -6.6169
Max Act: 5.9294. Min Act: -0.1700
Data Index: 2317278 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19