Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.7164. Min Act: -0.1700
Data Index: 3920910 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.6539. Min Act: -0.1700
Data Index: 7657989 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.4977. Min Act: -0.1700
Data Index: 5839595 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.5289. Min Act: -0.1700
Data Index: 2161101 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.5289. Min Act: -0.1700
Data Index: 6742132 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.4664. Min Act: -0.1700
Data Index: 7921585 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.4664. Min Act: -0.1700
Data Index: 4758886 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.4664. Min Act: -0.1700
Data Index: 1133194 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.4039. Min Act: -0.1700
Data Index: 6004561 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.4039. Min Act: -0.1700
Data Index: 7309201 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.4039. Min Act: -0.1700
Data Index: 1133195 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.4039. Min Act: -0.1700
Data Index: 2061422 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.3727. Min Act: -0.1700
Data Index: 7302237 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.3414. Min Act: -0.1700
Data Index: 712415 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.3102. Min Act: -0.1700
Data Index: 2815316 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.3102. Min Act: -0.1700
Data Index: 3927915 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.3102. Min Act: -0.1700
Data Index: 8198673 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.2789. Min Act: -0.1700
Data Index: 7029690 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.3102. Min Act: -0.1700
Data Index: 2438358 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7164. Min Range: -5.7164
Max Act: 5.3102. Min Act: -0.1700
Data Index: 4985172 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19