Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1763 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.3380. Min Act: -0.1700
Data Index: 7332903 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.3223. Min Act: -0.1700
Data Index: 3815374 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.3223. Min Act: -0.1700
Data Index: 1848387 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.3066. Min Act: -0.1700
Data Index: 8817119 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.3066. Min Act: -0.1700
Data Index: 1034110 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2909. Min Act: -0.1700
Data Index: 1696979 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2752. Min Act: -0.1700
Data Index: 5221819 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2752. Min Act: -0.1700
Data Index: 1404756 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2752. Min Act: -0.1700
Data Index: 3118932 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2595. Min Act: -0.1700
Data Index: 5491212 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2595. Min Act: -0.1700
Data Index: 6468321 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2595. Min Act: -0.1700
Data Index: 701843 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2438. Min Act: -0.1700
Data Index: 7558964 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2438. Min Act: -0.1700
Data Index: 2216529 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2438. Min Act: -0.1700
Data Index: 7075952 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2438. Min Act: -0.1700
Data Index: 5229607 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2438. Min Act: -0.1700
Data Index: 8654500 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2281. Min Act: -0.1700
Data Index: 4846245 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2281. Min Act: -0.1700
Data Index: 6066994 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3380. Min Range: -3.3380
Max Act: 3.2281. Min Act: -0.1700
Data Index: 5702520 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19