Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 868 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.4101. Min Act: -0.1700
Data Index: 1070363 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.3476. Min Act: -0.1700
Data Index: 1197893 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.3163. Min Act: -0.1700
Data Index: 5030847 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.3163. Min Act: -0.1700
Data Index: 988139 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.2226. Min Act: -0.1700
Data Index: 8394560 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.1913. Min Act: -0.1700
Data Index: 4357964 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.1601. Min Act: -0.1700
Data Index: 1450272 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.1601. Min Act: -0.1700
Data Index: 7602378 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.1601. Min Act: -0.1700
Data Index: 2483331 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.0976. Min Act: -0.1700
Data Index: 858328 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.0976. Min Act: -0.1700
Data Index: 3491287 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.0976. Min Act: -0.1700
Data Index: 4658131 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.0976. Min Act: -0.1700
Data Index: 1902711 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.0976. Min Act: -0.1700
Data Index: 5852432 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.0976. Min Act: -0.1700
Data Index: 4891354 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.0976. Min Act: -0.1700
Data Index: 8821992 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.0976. Min Act: -0.1700
Data Index: 6370417 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.0976. Min Act: -0.1700
Data Index: 2680656 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.0976. Min Act: -0.1700
Data Index: 2557906 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4101. Min Range: -5.4101
Max Act: 5.0351. Min Act: -0.1700
Data Index: 1810977 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19