Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4456 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5823. Min Range: -7.5823
Max Act: 7.5823. Min Act: -0.1700
Data Index: 6010838 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5823. Min Range: -7.5823
Max Act: 7.1135. Min Act: -0.1700
Data Index: 7585803 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.9885. Min Act: -0.1700
Data Index: 2541932 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.8010. Min Act: -0.1700
Data Index: 389807 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.7698. Min Act: -0.1700
Data Index: 3305766 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.7385. Min Act: -0.1700
Data Index: 5022356 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.7698. Min Act: -0.1700
Data Index: 4128127 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.7698. Min Act: -0.1700
Data Index: 7322728 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.5823. Min Act: -0.1700
Data Index: 5547700 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.5823. Min Act: -0.1700
Data Index: 6363114 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.5198. Min Act: -0.1700
Data Index: 5536427 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.4885. Min Act: -0.1700
Data Index: 1700204 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.4573. Min Act: -0.1700
Data Index: 8332847 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.4885. Min Act: -0.1700
Data Index: 7630327 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.4573. Min Act: -0.1700
Data Index: 6410511 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.4260. Min Act: -0.1700
Data Index: 6338701 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.4260. Min Act: -0.1700
Data Index: 8757723 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.4260. Min Act: -0.1700
Data Index: 4956841 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.3948. Min Act: -0.1700
Data Index: 6069078 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.4260. Min Act: -0.1700
Data Index: 5024075 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19