Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5797 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.7540. Min Act: -0.1700
Data Index: 2295947 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.5665. Min Act: -0.1700
Data Index: 1046875 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.5353. Min Act: -0.1700
Data Index: 8128658 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.4728. Min Act: -0.1700
Data Index: 7533949 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.4728. Min Act: -0.1700
Data Index: 177224 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.4415. Min Act: -0.1700
Data Index: 3117978 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.4103. Min Act: -0.1700
Data Index: 8014397 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.4103. Min Act: -0.1700
Data Index: 6993026 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.4103. Min Act: -0.1700
Data Index: 1349822 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.3790. Min Act: -0.1700
Data Index: 8469329 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.3790. Min Act: -0.1700
Data Index: 2167219 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.3790. Min Act: -0.1700
Data Index: 650320 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.3790. Min Act: -0.1700
Data Index: 77377 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.3790. Min Act: -0.1700
Data Index: 213076 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.3478. Min Act: -0.1700
Data Index: 6728341 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.3478. Min Act: -0.1700
Data Index: 3625269 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.3478. Min Act: -0.1700
Data Index: 7102959 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.3478. Min Act: -0.1700
Data Index: 916855 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.3165. Min Act: -0.1700
Data Index: 587109 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7540. Min Range: -6.7540
Max Act: 6.3165. Min Act: -0.1700
Data Index: 2146379 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19