Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 509 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.9420. Min Act: -0.1700
Data Index: 6222210 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.9420. Min Act: -0.1700
Data Index: 7011405 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.8795. Min Act: -0.1700
Data Index: 118059 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.8170. Min Act: -0.1700
Data Index: 6419798 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.7545. Min Act: -0.1700
Data Index: 8267081 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.7857. Min Act: -0.1700
Data Index: 1529815 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.7545. Min Act: -0.1700
Data Index: 6743578 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.7545. Min Act: -0.1700
Data Index: 4953288 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.7545. Min Act: -0.1700
Data Index: 6328425 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.7545. Min Act: -0.1700
Data Index: 8545680 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.7232. Min Act: -0.1700
Data Index: 2999993 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.7232. Min Act: -0.1700
Data Index: 85429 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.7232. Min Act: -0.1700
Data Index: 2286299 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.6920. Min Act: -0.1700
Data Index: 7305203 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.6920. Min Act: -0.1700
Data Index: 5940214 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.6920. Min Act: -0.1700
Data Index: 4714399 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.7232. Min Act: -0.1700
Data Index: 8592783 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.6920. Min Act: -0.1700
Data Index: 7696896 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.6607. Min Act: -0.1700
Data Index: 2127599 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9420. Min Range: -5.9420
Max Act: 5.6607. Min Act: -0.1700
Data Index: 8220262 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19