Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2881 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.5888. Min Act: -0.1700
Data Index: 1881266 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.4013. Min Act: -0.1700
Data Index: 7010332 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.3700. Min Act: -0.1700
Data Index: 6339088 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.3700. Min Act: -0.1700
Data Index: 4431702 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.3075. Min Act: -0.1700
Data Index: 6871732 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.2763. Min Act: -0.1700
Data Index: 1933301 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.2450. Min Act: -0.1700
Data Index: 1131459 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.2450. Min Act: -0.1700
Data Index: 1602074 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.2450. Min Act: -0.1700
Data Index: 4055470 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.1513. Min Act: -0.1700
Data Index: 6383036 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.1513. Min Act: -0.1700
Data Index: 1101130 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.1200. Min Act: -0.1700
Data Index: 5343753 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.1200. Min Act: -0.1700
Data Index: 3654255 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.1200. Min Act: -0.1700
Data Index: 3078178 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.1200. Min Act: -0.1700
Data Index: 5669663 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.1200. Min Act: -0.1700
Data Index: 5109089 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.0888. Min Act: -0.1700
Data Index: 3019649 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.0888. Min Act: -0.1700
Data Index: 3329506 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.0888. Min Act: -0.1700
Data Index: 4598292 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5888. Min Range: -5.5888
Max Act: 5.0575. Min Act: -0.1700
Data Index: 8439589 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19