Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2123 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2694. Min Range: -8.2694
Max Act: 8.2694. Min Act: -0.1700
Data Index: 4347160 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2694. Min Range: -8.2694
Max Act: 8.1132. Min Act: -0.1700
Data Index: 4131826 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2694. Min Range: -8.2694
Max Act: 8.0507. Min Act: -0.1700
Data Index: 4648840 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2694. Min Range: -8.2694
Max Act: 8.0194. Min Act: -0.1700
Data Index: 369226 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.9882. Min Act: -0.1700
Data Index: 1822010 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.9882. Min Act: -0.1700
Data Index: 6156645 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.9257. Min Act: -0.1700
Data Index: 6671354 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.8944. Min Act: -0.1700
Data Index: 1170142 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.9257. Min Act: -0.1700
Data Index: 7928600 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.8944. Min Act: -0.1700
Data Index: 1001884 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.8944. Min Act: -0.1700
Data Index: 8765754 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.8632. Min Act: -0.1700
Data Index: 2531473 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.8632. Min Act: -0.1700
Data Index: 8344784 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.8632. Min Act: -0.1699
Data Index: 7433275 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.8319. Min Act: -0.1700
Data Index: 5305501 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.8632. Min Act: -0.1700
Data Index: 6975295 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.8632. Min Act: -0.1700
Data Index: 5865449 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.8007. Min Act: -0.1700
Data Index: 7370098 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.7694. Min Act: -0.1700
Data Index: 453167 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2694. Min Range: -8.2694
Max Act: 7.8007. Min Act: -0.1700
Data Index: 5147220 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19