Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3251 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.8988. Min Act: -0.1700
Data Index: 6785245 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5863. Min Act: -0.1700
Data Index: 2358329 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.4925. Min Act: -0.1700
Data Index: 1800102 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.4300. Min Act: -0.1700
Data Index: 8695650 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.3675. Min Act: -0.1700
Data Index: 8399904 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.3050. Min Act: -0.1700
Data Index: 1632023 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.3050. Min Act: -0.1700
Data Index: 5586634 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.2738. Min Act: -0.1700
Data Index: 7161322 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.2425. Min Act: -0.1700
Data Index: 8081340 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.2425. Min Act: -0.1700
Data Index: 3080594 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.2425. Min Act: -0.1700
Data Index: 3874947 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.2113. Min Act: -0.1700
Data Index: 3970342 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.1800. Min Act: -0.1700
Data Index: 476649 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.1488. Min Act: -0.1700
Data Index: 986773 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.1488. Min Act: -0.1700
Data Index: 7642337 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.1488. Min Act: -0.1700
Data Index: 8373028 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.1488. Min Act: -0.1700
Data Index: 4881250 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.1175. Min Act: -0.1700
Data Index: 3224753 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.1175. Min Act: -0.1700
Data Index: 5292882 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.1175. Min Act: -0.1700
Data Index: 6384898 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19