Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2930 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.8238. Min Act: -0.1700
Data Index: 7815270 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.7768. Min Act: -0.1700
Data Index: 7243240 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.7143. Min Act: -0.1700
Data Index: 3515482 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.6517. Min Act: -0.1700
Data Index: 4089754 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.6517. Min Act: -0.1700
Data Index: 8751344 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.6204. Min Act: -0.1700
Data Index: 2982339 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.6361. Min Act: -0.1700
Data Index: 5978101 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.6204. Min Act: -0.1700
Data Index: 1265621 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.6204. Min Act: -0.1700
Data Index: 1925098 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.6048. Min Act: -0.1700
Data Index: 4082601 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.6048. Min Act: -0.1700
Data Index: 7139780 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.5735. Min Act: -0.1700
Data Index: 8451242 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.5891. Min Act: -0.1700
Data Index: 6959332 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.5891. Min Act: -0.1700
Data Index: 6327119 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.5735. Min Act: -0.1700
Data Index: 5554475 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.5735. Min Act: -0.1700
Data Index: 193314 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.5578. Min Act: -0.1700
Data Index: 2332738 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.5578. Min Act: -0.1700
Data Index: 6201400 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.5578. Min Act: -0.1700
Data Index: 555105 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8238. Min Range: -3.8238
Max Act: 3.5578. Min Act: -0.1700
Data Index: 7784317 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19