Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4697 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4219. Min Range: -5.4219
Max Act: 5.3907. Min Act: -0.1700
Data Index: 122679 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4219. Min Range: -5.4219
Max Act: 5.4219. Min Act: -0.1700
Data Index: 122691 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4219. Min Range: -5.4219
Max Act: 5.1719. Min Act: -0.1700
Data Index: 1796781 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4219. Min Range: -5.4219
Max Act: 5.1719. Min Act: -0.1700
Data Index: 1547242 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4219. Min Range: -5.4219
Max Act: 5.1719. Min Act: -0.1700
Data Index: 5050465 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4219. Min Range: -5.4219
Max Act: 5.0782. Min Act: -0.1700
Data Index: 8707200 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4219. Min Range: -5.4219
Max Act: 5.0469. Min Act: -0.1700
Data Index: 3854998 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4219. Min Range: -5.4219
Max Act: 5.0469. Min Act: -0.1700
Data Index: 1547219 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4219. Min Range: -5.4219
Max Act: 5.0469. Min Act: -0.1700
Data Index: 4768583 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4219. Min Range: -5.4219
Max Act: 5.0469. Min Act: -0.1700
Data Index: 6941408 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4219. Min Range: -5.4219
Max Act: 5.0469. Min Act: -0.1700
Data Index: 6640649 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4219. Min Range: -5.4219
Max Act: 5.0157. Min Act: -0.1700
Data Index: 4019288 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4219. Min Range: -5.4219
Max Act: 4.9844. Min Act: -0.1700
Data Index: 1547220 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4219. Min Range: -5.4219
Max Act: 4.9219. Min Act: -0.1700
Data Index: 3932981 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4219. Min Range: -5.4219
Max Act: 4.9219. Min Act: -0.1700
Data Index: 1341395 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4219. Min Range: -5.4219
Max Act: 4.8907. Min Act: -0.1700
Data Index: 7057311 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4219. Min Range: -5.4219
Max Act: 4.8594. Min Act: -0.1700
Data Index: 7110816 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4219. Min Range: -5.4219
Max Act: 4.8907. Min Act: -0.1700
Data Index: 1271644 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4219. Min Range: -5.4219
Max Act: 4.8594. Min Act: -0.1700
Data Index: 992364 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4219. Min Range: -5.4219
Max Act: 4.8282. Min Act: -0.1700
Data Index: 1065383 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19