Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3043 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4919. Min Range: -8.4919
Max Act: 8.4919. Min Act: -0.1700
Data Index: 1958539 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4919. Min Range: -8.4919
Max Act: 8.4919. Min Act: -0.1700
Data Index: 6794559 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4919. Min Range: -8.4919
Max Act: 8.4294. Min Act: -0.1700
Data Index: 4150229 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4919. Min Range: -8.4919
Max Act: 8.3044. Min Act: -0.1700
Data Index: 1825660 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4919. Min Range: -8.4919
Max Act: 8.2419. Min Act: -0.1700
Data Index: 3448791 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4919. Min Range: -8.4919
Max Act: 8.3044. Min Act: -0.1700
Data Index: 3825344 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4919. Min Range: -8.4919
Max Act: 8.2419. Min Act: -0.1700
Data Index: 6276432 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4919. Min Range: -8.4919
Max Act: 8.0544. Min Act: -0.1700
Data Index: 3041932 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4919. Min Range: -8.4919
Max Act: 8.0544. Min Act: -0.1700
Data Index: 8354087 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4919. Min Range: -8.4919
Max Act: 7.9919. Min Act: -0.1700
Data Index: 201351 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4919. Min Range: -8.4919
Max Act: 7.9919. Min Act: -0.1700
Data Index: 8020938 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4919. Min Range: -8.4919
Max Act: 7.9919. Min Act: -0.1700
Data Index: 8731430 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4919. Min Range: -8.4919
Max Act: 7.9919. Min Act: -0.1700
Data Index: 1761205 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4919. Min Range: -8.4919
Max Act: 7.9919. Min Act: -0.1700
Data Index: 6182904 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4919. Min Range: -8.4919
Max Act: 7.9919. Min Act: -0.1700
Data Index: 8255341 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4919. Min Range: -8.4919
Max Act: 7.8669. Min Act: -0.1700
Data Index: 546538 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4919. Min Range: -8.4919
Max Act: 7.8981. Min Act: -0.1700
Data Index: 5587460 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4919. Min Range: -8.4919
Max Act: 7.8981. Min Act: -0.1700
Data Index: 4116818 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4919. Min Range: -8.4919
Max Act: 7.8981. Min Act: -0.1700
Data Index: 1679471 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4919. Min Range: -8.4919
Max Act: 7.8981. Min Act: -0.1700
Data Index: 6028456 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19