Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 932 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.8190. Min Act: -0.1700
Data Index: 6030498 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.7253. Min Act: -0.1700
Data Index: 2829347 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.7253. Min Act: -0.1700
Data Index: 5989194 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.6940. Min Act: -0.1700
Data Index: 8584289 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.6315. Min Act: -0.1700
Data Index: 8824038 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.6315. Min Act: -0.1700
Data Index: 1973275 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.6315. Min Act: -0.1700
Data Index: 3682810 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.5378. Min Act: -0.1700
Data Index: 5423773 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.5378. Min Act: -0.1700
Data Index: 473381 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.5378. Min Act: -0.1700
Data Index: 6937055 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.5378. Min Act: -0.1700
Data Index: 8123450 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.4753. Min Act: -0.1700
Data Index: 5020155 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.4753. Min Act: -0.1700
Data Index: 5473640 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.4753. Min Act: -0.1700
Data Index: 7410783 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.4753. Min Act: -0.1700
Data Index: 6717957 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.4440. Min Act: -0.1700
Data Index: 1157160 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.4128. Min Act: -0.1700
Data Index: 8750883 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.4128. Min Act: -0.1700
Data Index: 4589849 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.3815. Min Act: -0.1700
Data Index: 4514778 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8190. Min Range: -5.8190
Max Act: 5.3815. Min Act: -0.1700
Data Index: 150032 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19