Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.3283. Min Act: -0.1700
Data Index: 5407368 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.3596. Min Act: -0.1700
Data Index: 1733041 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.3283. Min Act: -0.1700
Data Index: 6341607 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.3283. Min Act: -0.1700
Data Index: 3010529 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.2346. Min Act: -0.1700
Data Index: 2062677 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.2033. Min Act: -0.1700
Data Index: 6063261 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.2033. Min Act: -0.1700
Data Index: 4165716 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.1408. Min Act: -0.1700
Data Index: 5350507 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.1408. Min Act: -0.1700
Data Index: 6415778 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.1096. Min Act: -0.1700
Data Index: 5661851 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.1096. Min Act: -0.1700
Data Index: 4503276 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.1096. Min Act: -0.1700
Data Index: 2995218 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.0783. Min Act: -0.1700
Data Index: 6373627 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.0471. Min Act: -0.1700
Data Index: 8816443 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.0471. Min Act: -0.1700
Data Index: 3254603 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3596. Min Range: -6.3596
Max Act: 6.0471. Min Act: -0.1700
Data Index: 561832 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3596. Min Range: -6.3596
Max Act: 5.9846. Min Act: -0.1700
Data Index: 1927465 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3596. Min Range: -6.3596
Max Act: 5.9846. Min Act: -0.1700
Data Index: 8039818 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3596. Min Range: -6.3596
Max Act: 5.9846. Min Act: -0.1700
Data Index: 659930 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3596. Min Range: -6.3596
Max Act: 5.9846. Min Act: -0.1700
Data Index: 2940453 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19