Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4273 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.5071. Min Act: -0.1700
Data Index: 2228983 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.5071. Min Act: -0.1700
Data Index: 3071373 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.4758. Min Act: -0.1700
Data Index: 7921466 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.4444. Min Act: -0.1700
Data Index: 5458445 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.4444. Min Act: -0.1700
Data Index: 1816219 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.4288. Min Act: -0.1700
Data Index: 3864697 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.3660. Min Act: -0.1700
Data Index: 1106793 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.3660. Min Act: -0.1700
Data Index: 5827479 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.3504. Min Act: -0.1700
Data Index: 5223857 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.3347. Min Act: -0.1700
Data Index: 7994460 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.3504. Min Act: -0.1700
Data Index: 6085102 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.3190. Min Act: -0.1700
Data Index: 3264324 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.3033. Min Act: -0.1700
Data Index: 8063445 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.3033. Min Act: -0.1700
Data Index: 8322035 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.3033. Min Act: -0.1700
Data Index: 5822287 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.3033. Min Act: -0.1700
Data Index: 2476654 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.3033. Min Act: -0.1700
Data Index: 8523236 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.2876. Min Act: -0.1700
Data Index: 1447419 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.2719. Min Act: -0.1700
Data Index: 4588526 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5071. Min Range: -3.5071
Max Act: 3.2876. Min Act: -0.1700
Data Index: 1611157 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19