Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3949 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.7656. Min Act: -0.1691
Data Index: 7342144 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.7325. Min Act: -0.1698
Data Index: 7563512 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.7161. Min Act: -0.1698
Data Index: 8017459 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6753. Min Act: -0.1700
Data Index: 7224796 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6753. Min Act: -0.1700
Data Index: 659571 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6835. Min Act: -0.1700
Data Index: 1736434 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6835. Min Act: -0.1700
Data Index: 4372623 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6753. Min Act: -0.1700
Data Index: 2900504 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6512. Min Act: -0.1699
Data Index: 6317897 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6512. Min Act: -0.1700
Data Index: 1743078 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6512. Min Act: -0.1697
Data Index: 2568735 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6512. Min Act: -0.1700
Data Index: 4868463 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6512. Min Act: -0.1700
Data Index: 3774899 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6432. Min Act: -0.1697
Data Index: 6908940 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6432. Min Act: -0.1700
Data Index: 3131931 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6432. Min Act: -0.1691
Data Index: 4750076 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6512. Min Act: -0.1700
Data Index: 5850021 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6352. Min Act: -0.1698
Data Index: 6317896 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6272. Min Act: -0.1700
Data Index: 870104 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7656. Min Range: -0.7656
Max Act: 0.6272. Min Act: -0.1700
Data Index: 3111650 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19