Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1626 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0266. Min Range: -7.0266
Max Act: 7.0266. Min Act: -0.1700
Data Index: 7962595 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.9954. Min Act: -0.1700
Data Index: 4579246 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.9641. Min Act: -0.1700
Data Index: 2644864 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.8704. Min Act: -0.1700
Data Index: 8328718 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.8391. Min Act: -0.1700
Data Index: 6964821 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.8391. Min Act: -0.1700
Data Index: 8268826 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.8391. Min Act: -0.1700
Data Index: 8625072 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.7766. Min Act: -0.1700
Data Index: 8446429 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.7141. Min Act: -0.1700
Data Index: 4683574 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.7141. Min Act: -0.1700
Data Index: 3693811 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.7141. Min Act: -0.1700
Data Index: 8537580 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.6829. Min Act: -0.1700
Data Index: 3100551 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.6829. Min Act: -0.1700
Data Index: 2792932 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.6516. Min Act: -0.1700
Data Index: 2727242 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.6516. Min Act: -0.1700
Data Index: 2640003 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.6516. Min Act: -0.1700
Data Index: 2111164 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.6516. Min Act: -0.1700
Data Index: 7621053 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.6204. Min Act: -0.1700
Data Index: 850944 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.5891. Min Act: -0.1700
Data Index: 4203119 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0266. Min Range: -7.0266
Max Act: 6.5891. Min Act: -0.1700
Data Index: 4245560 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19