Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3885 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.9670. Min Act: -0.1700
Data Index: 6536533 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.9670. Min Act: -0.1700
Data Index: 380430 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.8420. Min Act: -0.1700
Data Index: 1410350 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.7795. Min Act: -0.1700
Data Index: 7536350 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.4670. Min Act: -0.1700
Data Index: 1800345 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.4045. Min Act: -0.1700
Data Index: 8324872 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.4045. Min Act: -0.1700
Data Index: 1991830 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.2795. Min Act: -0.1700
Data Index: 7687215 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.2795. Min Act: -0.1700
Data Index: 486342 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.2795. Min Act: -0.1700
Data Index: 2871250 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.2795. Min Act: -0.1700
Data Index: 1332837 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.2795. Min Act: -0.1700
Data Index: 1689326 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.2795. Min Act: -0.1700
Data Index: 4999531 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.2795. Min Act: -0.1700
Data Index: 1500014 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.2170. Min Act: -0.1700
Data Index: 2417604 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.1545. Min Act: -0.1700
Data Index: 879597 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.2170. Min Act: -0.1700
Data Index: 6602683 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.2170. Min Act: -0.1700
Data Index: 4546532 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.2170. Min Act: -0.1700
Data Index: 6245627 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9670. Min Range: -9.9670
Max Act: 9.2170. Min Act: -0.1700
Data Index: 2423476 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19