Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2765. Min Range: -9.2765
Max Act: 9.2765. Min Act: -0.1700
Data Index: 5421115 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.5265. Min Act: -0.1700
Data Index: 7637591 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.5265. Min Act: -0.1700
Data Index: 3262971 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.4640. Min Act: -0.1700
Data Index: 3492829 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.3390. Min Act: -0.1700
Data Index: 3237781 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.2765. Min Act: -0.1700
Data Index: 3994381 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.2765. Min Act: -0.1700
Data Index: 8279145 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.2765. Min Act: -0.1700
Data Index: 6065808 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.1515. Min Act: -0.1700
Data Index: 4959207 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.2140. Min Act: -0.1700
Data Index: 3296341 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.2140. Min Act: -0.1700
Data Index: 2095796 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.2140. Min Act: -0.1700
Data Index: 6549354 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.2140. Min Act: -0.1700
Data Index: 6640576 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.1515. Min Act: -0.1700
Data Index: 102457 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.0890. Min Act: -0.1700
Data Index: 8229198 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.0890. Min Act: -0.1700
Data Index: 2950845 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.1515. Min Act: -0.1700
Data Index: 2932927 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.1515. Min Act: -0.1700
Data Index: 6078330 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.1515. Min Act: -0.1700
Data Index: 1572859 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2765. Min Range: -9.2765
Max Act: 8.0890. Min Act: -0.1700
Data Index: 586272 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19