Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3316 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3686. Min Act: -0.1700
Data Index: 7196409 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3686. Min Act: -0.1700
Data Index: 5326964 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3686. Min Act: -0.1700
Data Index: 8372703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3372. Min Act: -0.1700
Data Index: 4961402 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3058. Min Act: -0.1700
Data Index: 4757625 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3058. Min Act: -0.1700
Data Index: 5930320 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3058. Min Act: -0.1700
Data Index: 5605140 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3372. Min Act: -0.1700
Data Index: 728679 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3058. Min Act: -0.1700
Data Index: 1785448 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3058. Min Act: -0.1700
Data Index: 4730568 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3058. Min Act: -0.1700
Data Index: 2306016 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3058. Min Act: -0.1700
Data Index: 7635207 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3058. Min Act: -0.1700
Data Index: 3625142 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.3058. Min Act: -0.1700
Data Index: 6281232 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.2744. Min Act: -0.1700
Data Index: 4639408 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.2744. Min Act: -0.1700
Data Index: 473357 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.2744. Min Act: -0.1700
Data Index: 5319399 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.2744. Min Act: -0.1700
Data Index: 1512458 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.2744. Min Act: -0.1700
Data Index: 5451427 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3686. Min Range: -3.3686
Max Act: 3.2744. Min Act: -0.1700
Data Index: 3262726 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19