Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.6092. Min Act: -0.1700
Data Index: 42071 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.5780. Min Act: -0.1700
Data Index: 4029085 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.4530. Min Act: -0.1700
Data Index: 2927873 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.4530. Min Act: -0.1700
Data Index: 192039 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.4842. Min Act: -0.1700
Data Index: 6496413 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.4217. Min Act: -0.1700
Data Index: 4979960 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.4217. Min Act: -0.1700
Data Index: 1746005 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.4530. Min Act: -0.1700
Data Index: 8448407 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.4217. Min Act: -0.1700
Data Index: 6814807 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.3905. Min Act: -0.1700
Data Index: 3430415 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.3905. Min Act: -0.1700
Data Index: 3107741 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.4217. Min Act: -0.1700
Data Index: 8101569 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.3905. Min Act: -0.1700
Data Index: 167873 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.3905. Min Act: -0.1700
Data Index: 58104 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.3905. Min Act: -0.1700
Data Index: 5859210 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.3905. Min Act: -0.1700
Data Index: 1257337 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.3905. Min Act: -0.1700
Data Index: 8801350 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.3592. Min Act: -0.1700
Data Index: 979494 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.3905. Min Act: -0.1700
Data Index: 7516319 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6092. Min Range: -4.6092
Max Act: 4.3280. Min Act: -0.1700
Data Index: 7890460 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19