Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5655 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.9742. Min Act: -0.1700
Data Index: 957558 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.8804. Min Act: -0.1700
Data Index: 6273714 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.8492. Min Act: -0.1700
Data Index: 7987506 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.8179. Min Act: -0.1700
Data Index: 3183562 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.6929. Min Act: -0.1700
Data Index: 5724194 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.6617. Min Act: -0.1700
Data Index: 5690952 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.6304. Min Act: -0.1700
Data Index: 8279256 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.5992. Min Act: -0.1700
Data Index: 7140423 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.5679. Min Act: -0.1700
Data Index: 3204013 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.5679. Min Act: -0.1700
Data Index: 4978759 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.5679. Min Act: -0.1700
Data Index: 4305169 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.5054. Min Act: -0.1700
Data Index: 1050799 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.5367. Min Act: -0.1700
Data Index: 4808742 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.4742. Min Act: -0.1700
Data Index: 2009592 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.4742. Min Act: -0.1700
Data Index: 6515598 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.4429. Min Act: -0.1700
Data Index: 1348491 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.4429. Min Act: -0.1700
Data Index: 1206724 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.4429. Min Act: -0.1700
Data Index: 7257448 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.4429. Min Act: -0.1700
Data Index: 2350923 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9742. Min Range: -5.9742
Max Act: 5.4429. Min Act: -0.1700
Data Index: 4747873 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19