Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.6295. Min Act: -0.1700
Data Index: 256155 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.6295. Min Act: -0.1700
Data Index: 6652678 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.5670. Min Act: -0.1700
Data Index: 6072346 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.5670. Min Act: -0.1700
Data Index: 1129496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.5045. Min Act: -0.1700
Data Index: 6742098 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.3795. Min Act: -0.1700
Data Index: 6539516 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.4420. Min Act: -0.1700
Data Index: 2197875 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.4420. Min Act: -0.1700
Data Index: 8528333 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.4420. Min Act: -0.1700
Data Index: 7580269 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.4420. Min Act: -0.1700
Data Index: 949290 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.4420. Min Act: -0.1700
Data Index: 1823511 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.4420. Min Act: -0.1700
Data Index: 1745409 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.4420. Min Act: -0.1700
Data Index: 6562269 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.4420. Min Act: -0.1700
Data Index: 1615067 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.4420. Min Act: -0.1700
Data Index: 5556277 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.5045. Min Act: -0.1700
Data Index: 5266383 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.4420. Min Act: -0.1700
Data Index: 4422780 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.4420. Min Act: -0.1700
Data Index: 4294391 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.4420. Min Act: -0.1700
Data Index: 3992770 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6295. Min Range: -7.6295
Max Act: 7.4420. Min Act: -0.1698
Data Index: 3195585 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19