Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3418 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0744. Min Range: -6.0744
Max Act: 6.0744. Min Act: -0.1700
Data Index: 7715261 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.8869. Min Act: -0.1700
Data Index: 3825545 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.8869. Min Act: -0.1700
Data Index: 7306901 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.8557. Min Act: -0.1700
Data Index: 2326440 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.7619. Min Act: -0.1700
Data Index: 438571 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.7619. Min Act: -0.1700
Data Index: 1696563 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6994. Min Act: -0.1700
Data Index: 3851468 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6994. Min Act: -0.1700
Data Index: 8104989 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6994. Min Act: -0.1700
Data Index: 1305402 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6994. Min Act: -0.1700
Data Index: 4408055 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6994. Min Act: -0.1700
Data Index: 1651871 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6057. Min Act: -0.1700
Data Index: 8448755 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6057. Min Act: -0.1700
Data Index: 5214819 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6057. Min Act: -0.1700
Data Index: 7866479 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.5432. Min Act: -0.1700
Data Index: 4924673 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.5119. Min Act: -0.1700
Data Index: 3656339 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.5119. Min Act: -0.1700
Data Index: 2687502 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.4807. Min Act: -0.1700
Data Index: 3022251 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.4807. Min Act: -0.1700
Data Index: 3342920 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.4807. Min Act: -0.1700
Data Index: 3968289 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19