Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2860 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3903. Min Range: -10.3903
Max Act: 10.3903. Min Act: -0.1700
Data Index: 8512875 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3903. Min Range: -10.3903
Max Act: 10.1403. Min Act: -0.1700
Data Index: 3922320 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.9528. Min Act: -0.1700
Data Index: 203984 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.7028. Min Act: -0.1700
Data Index: 455780 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.7028. Min Act: -0.1700
Data Index: 6232430 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.7028. Min Act: -0.1700
Data Index: 940026 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.6403. Min Act: -0.1700
Data Index: 4545758 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.6403. Min Act: -0.1700
Data Index: 8762033 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.5778. Min Act: -0.1700
Data Index: 484948 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.5778. Min Act: -0.1700
Data Index: 877306 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.5778. Min Act: -0.1700
Data Index: 2330834 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.5153. Min Act: -0.1700
Data Index: 14926 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.4528. Min Act: -0.1700
Data Index: 8303427 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.3903. Min Act: -0.1700
Data Index: 450991 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.4528. Min Act: -0.1700
Data Index: 6734294 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.3903. Min Act: -0.1700
Data Index: 1203382 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.3903. Min Act: -0.1700
Data Index: 8059855 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.3903. Min Act: -0.1700
Data Index: 4295345 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.3278. Min Act: -0.1700
Data Index: 6941153 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3903. Min Range: -10.3903
Max Act: 9.3278. Min Act: -0.1700
Data Index: 3011486 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19