Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 987 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.3200. Min Act: -0.1700
Data Index: 6042224 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.2263. Min Act: -0.1700
Data Index: 1768162 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.2263. Min Act: -0.1700
Data Index: 1309344 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.1950. Min Act: -0.1700
Data Index: 8115736 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.1950. Min Act: -0.1700
Data Index: 8683139 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.1950. Min Act: -0.1700
Data Index: 5874930 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.1638. Min Act: -0.1700
Data Index: 6308068 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.1638. Min Act: -0.1700
Data Index: 205413 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.1325. Min Act: -0.1700
Data Index: 2728655 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.1325. Min Act: -0.1700
Data Index: 4012043 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.1325. Min Act: -0.1700
Data Index: 5286764 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.1012. Min Act: -0.1700
Data Index: 1814303 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.0700. Min Act: -0.1700
Data Index: 6750445 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.0387. Min Act: -0.1700
Data Index: 6759806 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.0700. Min Act: -0.1700
Data Index: 1643797 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.0387. Min Act: -0.1700
Data Index: 8474646 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.0387. Min Act: -0.1700
Data Index: 2859858 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.0387. Min Act: -0.1700
Data Index: 2833628 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.0387. Min Act: -0.1700
Data Index: 7779841 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3200. Min Range: -4.3200
Max Act: 4.0387. Min Act: -0.1700
Data Index: 3627158 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19