Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2953 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.8761. Min Act: -0.1700
Data Index: 3142556 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.6261. Min Act: -0.1700
Data Index: 7938441 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.6261. Min Act: -0.1700
Data Index: 1498953 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.6261. Min Act: -0.1700
Data Index: 6694283 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.6261. Min Act: -0.1700
Data Index: 2083654 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.6261. Min Act: -0.1700
Data Index: 7513705 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.6573. Min Act: -0.1700
Data Index: 1632418 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5948. Min Act: -0.1700
Data Index: 5507389 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5948. Min Act: -0.1700
Data Index: 5196805 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5948. Min Act: -0.1700
Data Index: 1984632 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5323. Min Act: -0.1700
Data Index: 5973999 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5323. Min Act: -0.1700
Data Index: 1643713 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5636. Min Act: -0.1700
Data Index: 7676047 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.4698. Min Act: -0.1700
Data Index: 5924485 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5011. Min Act: -0.1700
Data Index: 8293457 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5011. Min Act: -0.1700
Data Index: 4994731 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5011. Min Act: -0.1700
Data Index: 4129194 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5011. Min Act: -0.1700
Data Index: 4922050 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.4698. Min Act: -0.1700
Data Index: 7319536 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.4698. Min Act: -0.1700
Data Index: 3157261 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19