Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.8325. Min Act: -0.1700
Data Index: 6386864 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.6763. Min Act: -0.1700
Data Index: 4965591 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.6138. Min Act: -0.1700
Data Index: 3132215 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.6138. Min Act: -0.1700
Data Index: 2860399 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.5825. Min Act: -0.1700
Data Index: 8404049 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.4888. Min Act: -0.1700
Data Index: 2483834 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.4575. Min Act: -0.1700
Data Index: 4795819 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.4575. Min Act: -0.1700
Data Index: 4795832 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.4575. Min Act: -0.1700
Data Index: 7615526 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.4888. Min Act: -0.1700
Data Index: 2699158 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.4575. Min Act: -0.1700
Data Index: 1742003 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.4263. Min Act: -0.1700
Data Index: 2470261 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.4263. Min Act: -0.1700
Data Index: 5463592 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.3950. Min Act: -0.1700
Data Index: 7728589 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.3950. Min Act: -0.1700
Data Index: 1420804 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.3950. Min Act: -0.1700
Data Index: 1637423 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.3950. Min Act: -0.1700
Data Index: 5172742 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.3638. Min Act: -0.1700
Data Index: 6249050 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.3638. Min Act: -0.1700
Data Index: 3836740 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8325. Min Range: -5.8325
Max Act: 5.3325. Min Act: -0.1700
Data Index: 290861 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19