Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2492 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.7114. Min Act: -0.1700
Data Index: 7018037 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.6489. Min Act: -0.1700
Data Index: 2529124 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.6489. Min Act: -0.1700
Data Index: 7302209 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.6177. Min Act: -0.1700
Data Index: 6369480 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.6177. Min Act: -0.1700
Data Index: 5285020 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.6177. Min Act: -0.1700
Data Index: 211938 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5864. Min Act: -0.1700
Data Index: 4514405 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5864. Min Act: -0.1700
Data Index: 2910808 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5552. Min Act: -0.1700
Data Index: 6040056 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5552. Min Act: -0.1700
Data Index: 5419155 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5552. Min Act: -0.1700
Data Index: 5315939 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5552. Min Act: -0.1700
Data Index: 4020097 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5552. Min Act: -0.1700
Data Index: 2614342 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5552. Min Act: -0.1700
Data Index: 6560767 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5864. Min Act: -0.1700
Data Index: 237478 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5239. Min Act: -0.1700
Data Index: 2709080 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5552. Min Act: -0.1700
Data Index: 3818522 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5239. Min Act: -0.1700
Data Index: 4831834 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5552. Min Act: -0.1700
Data Index: 2150163 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7114. Min Range: -5.7114
Max Act: 5.5239. Min Act: -0.1700
Data Index: 5556725 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19