Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4004 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.5626. Min Act: -0.1700
Data Index: 4040267 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.5001. Min Act: -0.1700
Data Index: 3685151 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.4376. Min Act: -0.1700
Data Index: 337664 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.4064. Min Act: -0.1700
Data Index: 2100138 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.3751. Min Act: -0.1700
Data Index: 3794474 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.3439. Min Act: -0.1700
Data Index: 447602 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.2814. Min Act: -0.1700
Data Index: 3136624 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.2814. Min Act: -0.1700
Data Index: 7975883 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.2501. Min Act: -0.1700
Data Index: 6917172 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.2501. Min Act: -0.1700
Data Index: 7605614 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.2501. Min Act: -0.1700
Data Index: 3974305 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.1876. Min Act: -0.1700
Data Index: 7407619 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.1876. Min Act: -0.1700
Data Index: 2295093 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.1876. Min Act: -0.1700
Data Index: 4541734 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.1876. Min Act: -0.1700
Data Index: 1477651 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.1564. Min Act: -0.1700
Data Index: 4788881 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.1564. Min Act: -0.1700
Data Index: 7981766 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.1564. Min Act: -0.1700
Data Index: 887335 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.1251. Min Act: -0.1700
Data Index: 6676124 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5626. Min Range: -5.5626
Max Act: 5.1251. Min Act: -0.1700
Data Index: 6758562 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19