Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4787 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0084. Min Range: -5.0084
Max Act: 5.0084. Min Act: -0.1700
Data Index: 5912871 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.9147. Min Act: -0.1700
Data Index: 6635276 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.9147. Min Act: -0.1700
Data Index: 3948599 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.8834. Min Act: -0.1700
Data Index: 6215610 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.8834. Min Act: -0.1700
Data Index: 234642 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.8209. Min Act: -0.1700
Data Index: 5607562 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.8209. Min Act: -0.1700
Data Index: 4529090 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.8209. Min Act: -0.1700
Data Index: 4906193 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.8209. Min Act: -0.1700
Data Index: 7825476 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.7897. Min Act: -0.1700
Data Index: 5804029 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.7897. Min Act: -0.1700
Data Index: 3408362 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.7897. Min Act: -0.1700
Data Index: 5815566 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.7584. Min Act: -0.1700
Data Index: 5258913 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.7272. Min Act: -0.1700
Data Index: 8656888 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.7272. Min Act: -0.1700
Data Index: 7634528 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.6959. Min Act: -0.1700
Data Index: 7159870 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.7272. Min Act: -0.1700
Data Index: 4706880 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.7272. Min Act: -0.1700
Data Index: 1929160 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.6959. Min Act: -0.1700
Data Index: 4196120 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0084. Min Range: -5.0084
Max Act: 4.7272. Min Act: -0.1700
Data Index: 6450225 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19