Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7833. Min Range: -6.7833
Max Act: 6.7833. Min Act: -0.1700
Data Index: 5378653 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7833. Min Range: -6.7833
Max Act: 6.3458. Min Act: -0.1700
Data Index: 8025869 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7833. Min Range: -6.7833
Max Act: 6.3771. Min Act: -0.1700
Data Index: 6645172 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7833. Min Range: -6.7833
Max Act: 6.3146. Min Act: -0.1700
Data Index: 4586375 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7833. Min Range: -6.7833
Max Act: 6.1896. Min Act: -0.1700
Data Index: 7672329 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7833. Min Range: -6.7833
Max Act: 6.1271. Min Act: -0.1700
Data Index: 3217611 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7833. Min Range: -6.7833
Max Act: 6.0333. Min Act: -0.1700
Data Index: 3435722 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7833. Min Range: -6.7833
Max Act: 5.9396. Min Act: -0.1700
Data Index: 2570776 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7833. Min Range: -6.7833
Max Act: 5.9396. Min Act: -0.1700
Data Index: 5296217 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7833. Min Range: -6.7833
Max Act: 5.9083. Min Act: -0.1700
Data Index: 1111271 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7833. Min Range: -6.7833
Max Act: 5.9396. Min Act: -0.1700
Data Index: 7800332 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7833. Min Range: -6.7833
Max Act: 5.9396. Min Act: -0.1700
Data Index: 7786841 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7833. Min Range: -6.7833
Max Act: 5.9083. Min Act: -0.1700
Data Index: 3516361 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7833. Min Range: -6.7833
Max Act: 5.8771. Min Act: -0.1700
Data Index: 238489 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7833. Min Range: -6.7833
Max Act: 5.8771. Min Act: -0.1700
Data Index: 5339091 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7833. Min Range: -6.7833
Max Act: 5.8771. Min Act: -0.1700
Data Index: 6803920 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7833. Min Range: -6.7833
Max Act: 5.8458. Min Act: -0.1700
Data Index: 5754997 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7833. Min Range: -6.7833
Max Act: 5.8146. Min Act: -0.1700
Data Index: 8801138 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7833. Min Range: -6.7833
Max Act: 5.8146. Min Act: -0.1700
Data Index: 8456064 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7833. Min Range: -6.7833
Max Act: 5.8146. Min Act: -0.1700
Data Index: 375555 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19