Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4036 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.3482. Min Act: -0.1700
Data Index: 2338039 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.2225. Min Act: -0.1700
Data Index: 3755043 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.2225. Min Act: -0.1700
Data Index: 6475803 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.2225. Min Act: -0.1700
Data Index: 6486534 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.1754. Min Act: -0.1700
Data Index: 3333479 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.1281. Min Act: -0.1700
Data Index: 7668990 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.1124. Min Act: -0.1700
Data Index: 4800595 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.1124. Min Act: -0.1700
Data Index: 4052802 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.0809. Min Act: -0.1700
Data Index: 5230830 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.0651. Min Act: -0.1700
Data Index: 6486532 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.0651. Min Act: -0.1700
Data Index: 5741287 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.0651. Min Act: -0.1700
Data Index: 7334050 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.0335. Min Act: -0.1700
Data Index: 7500737 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.0177. Min Act: -0.1700
Data Index: 3755044 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.0335. Min Act: -0.1700
Data Index: 4017055 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.0177. Min Act: -0.1700
Data Index: 4865393 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.0177. Min Act: -0.1700
Data Index: 7800336 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.0177. Min Act: -0.1700
Data Index: 5483430 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.0019. Min Act: -0.1700
Data Index: 7705551 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3482. Min Range: -3.3482
Max Act: 3.0177. Min Act: -0.1700
Data Index: 8238148 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19