Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2344. Min Range: -4.2344
Max Act: 4.2344. Min Act: -0.1700
Data Index: 7489529 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2344. Min Range: -4.2344
Max Act: 4.1719. Min Act: -0.1700
Data Index: 4244544 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2344. Min Range: -4.2344
Max Act: 4.0469. Min Act: -0.1700
Data Index: 8236837 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2344. Min Range: -4.2344
Max Act: 4.0469. Min Act: -0.1700
Data Index: 8303396 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2344. Min Range: -4.2344
Max Act: 4.0156. Min Act: -0.1700
Data Index: 1777763 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2344. Min Range: -4.2344
Max Act: 4.0156. Min Act: -0.1700
Data Index: 2802539 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.9844. Min Act: -0.1700
Data Index: 3278059 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.9531. Min Act: -0.1700
Data Index: 514045 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.9844. Min Act: -0.1700
Data Index: 7959878 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.9531. Min Act: -0.1700
Data Index: 5503318 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.9531. Min Act: -0.1700
Data Index: 5210359 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.9531. Min Act: -0.1700
Data Index: 1395822 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.9219. Min Act: -0.1700
Data Index: 7557095 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.9844. Min Act: -0.1700
Data Index: 6437801 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.9531. Min Act: -0.1700
Data Index: 4408082 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.9531. Min Act: -0.1700
Data Index: 7646449 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.9531. Min Act: -0.1700
Data Index: 7654399 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.9219. Min Act: -0.1700
Data Index: 1625777 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.8906. Min Act: -0.1700
Data Index: 3211774 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2344. Min Range: -4.2344
Max Act: 3.8906. Min Act: -0.1700
Data Index: 2155544 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19