Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 630 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.6334. Min Act: -0.1700
Data Index: 336829 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.6021. Min Act: -0.1700
Data Index: 2178538 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.5239. Min Act: -0.1700
Data Index: 8209016 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.5239. Min Act: -0.1700
Data Index: 5705412 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.5082. Min Act: -0.1700
Data Index: 2478351 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.4769. Min Act: -0.1700
Data Index: 2634595 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.4769. Min Act: -0.1700
Data Index: 8042267 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.4769. Min Act: -0.1700
Data Index: 7882090 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.4612. Min Act: -0.1700
Data Index: 2975870 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.4612. Min Act: -0.1700
Data Index: 4678298 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.4612. Min Act: -0.1700
Data Index: 1253585 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.4612. Min Act: -0.1700
Data Index: 4686596 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.4299. Min Act: -0.1700
Data Index: 8209015 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.4455. Min Act: -0.1700
Data Index: 6428306 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.4299. Min Act: -0.1700
Data Index: 7302285 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.4142. Min Act: -0.1700
Data Index: 4778149 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.3985. Min Act: -0.1700
Data Index: 3312715 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.3985. Min Act: -0.1700
Data Index: 3985715 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.3828. Min Act: -0.1700
Data Index: 5612682 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6334. Min Range: -3.6334
Max Act: 3.3828. Min Act: -0.1700
Data Index: 4913428 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19