Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5275 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.8675. Min Act: -0.1700
Data Index: 7219099 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.7113. Min Act: -0.1700
Data Index: 4731364 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.7113. Min Act: -0.1700
Data Index: 1230782 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.6800. Min Act: -0.1700
Data Index: 6594135 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.7113. Min Act: -0.1700
Data Index: 84718 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.5863. Min Act: -0.1700
Data Index: 1910289 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.5238. Min Act: -0.1700
Data Index: 512538 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.4613. Min Act: -0.1700
Data Index: 178169 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.4925. Min Act: -0.1700
Data Index: 4249084 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.4925. Min Act: -0.1700
Data Index: 7357859 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.4925. Min Act: -0.1700
Data Index: 6137848 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.3988. Min Act: -0.1700
Data Index: 1369355 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.3988. Min Act: -0.1700
Data Index: 6722688 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.3988. Min Act: -0.1700
Data Index: 3754056 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.3988. Min Act: -0.1700
Data Index: 6032210 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.3988. Min Act: -0.1700
Data Index: 7284939 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.3988. Min Act: -0.1700
Data Index: 512539 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.3988. Min Act: -0.1700
Data Index: 2050998 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.3675. Min Act: -0.1700
Data Index: 2206664 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8675. Min Range: -5.8675
Max Act: 5.3675. Min Act: -0.1700
Data Index: 2582307 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19