Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5491 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.6648. Min Act: -0.1700
Data Index: 2230025 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.3523. Min Act: -0.1700
Data Index: 7511361 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.3210. Min Act: -0.1700
Data Index: 5204116 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.3210. Min Act: -0.1700
Data Index: 8503207 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.3210. Min Act: -0.1700
Data Index: 4113141 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.2585. Min Act: -0.1700
Data Index: 8576599 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.1960. Min Act: -0.1700
Data Index: 4129641 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.1960. Min Act: -0.1700
Data Index: 4066831 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.1960. Min Act: -0.1700
Data Index: 6147789 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.1648. Min Act: -0.1700
Data Index: 2425555 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.1648. Min Act: -0.1700
Data Index: 2393874 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.1648. Min Act: -0.1700
Data Index: 7802362 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.1648. Min Act: -0.1700
Data Index: 6324043 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.1335. Min Act: -0.1700
Data Index: 7308681 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.1335. Min Act: -0.1700
Data Index: 2239580 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.1335. Min Act: -0.1700
Data Index: 8536165 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.1023. Min Act: -0.1700
Data Index: 7227988 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.1023. Min Act: -0.1700
Data Index: 47539 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.1023. Min Act: -0.1700
Data Index: 1663992 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6648. Min Range: -7.6648
Max Act: 7.0398. Min Act: -0.1700
Data Index: 2008200 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19