Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2670 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2795. Min Range: -8.2795
Max Act: 8.2795. Min Act: -0.1700
Data Index: 1109033 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.7795. Min Act: -0.1700
Data Index: 5975343 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.4983. Min Act: -0.1700
Data Index: 1491223 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.4983. Min Act: -0.1700
Data Index: 2392549 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.4670. Min Act: -0.1700
Data Index: 4457527 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.4045. Min Act: -0.1700
Data Index: 251508 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.3420. Min Act: -0.1700
Data Index: 2136653 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.2795. Min Act: -0.1700
Data Index: 5140297 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.3108. Min Act: -0.1700
Data Index: 2321952 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.2483. Min Act: -0.1700
Data Index: 336659 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.2170. Min Act: -0.1700
Data Index: 4225879 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.2170. Min Act: -0.1700
Data Index: 2650028 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.1858. Min Act: -0.1700
Data Index: 8821695 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.1858. Min Act: -0.1700
Data Index: 1574242 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.1233. Min Act: -0.1700
Data Index: 1282521 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.1233. Min Act: -0.1700
Data Index: 3061757 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.0920. Min Act: -0.1700
Data Index: 8826663 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.1233. Min Act: -0.1700
Data Index: 805872 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.1233. Min Act: -0.1700
Data Index: 1453453 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2795. Min Range: -8.2795
Max Act: 7.0920. Min Act: -0.1700
Data Index: 1888208 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19