Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0269. Min Range: -3.0269
Max Act: 3.0269. Min Act: -0.1700
Data Index: 7751351 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.9161. Min Act: -0.1700
Data Index: 4969097 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.9003. Min Act: -0.1700
Data Index: 4345469 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.9003. Min Act: -0.1700
Data Index: 5539593 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.8844. Min Act: -0.1700
Data Index: 599292 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.8685. Min Act: -0.1700
Data Index: 5899061 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.8526. Min Act: -0.1700
Data Index: 2784755 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.8368. Min Act: -0.1700
Data Index: 6289523 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.8368. Min Act: -0.1700
Data Index: 8044413 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.8368. Min Act: -0.1700
Data Index: 3106336 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.8208. Min Act: -0.1700
Data Index: 2763658 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.8208. Min Act: -0.1700
Data Index: 7962783 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.8208. Min Act: -0.1700
Data Index: 5934370 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.8208. Min Act: -0.1700
Data Index: 4877151 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.8208. Min Act: -0.1700
Data Index: 67453 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.7890. Min Act: -0.1700
Data Index: 5609244 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.8049. Min Act: -0.1700
Data Index: 3900942 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.7890. Min Act: -0.1700
Data Index: 3899942 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.7890. Min Act: -0.1700
Data Index: 5398432 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0269. Min Range: -3.0269
Max Act: 2.7890. Min Act: -0.1700
Data Index: 4840200 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19