Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 874 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.4942. Min Act: -0.1700
Data Index: 1147261 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.4942. Min Act: -0.1700
Data Index: 2639045 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.4630. Min Act: -0.1700
Data Index: 6111103 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.4005. Min Act: -0.1700
Data Index: 7044222 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.3067. Min Act: -0.1700
Data Index: 430881 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.3067. Min Act: -0.1700
Data Index: 7384280 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.2442. Min Act: -0.1700
Data Index: 8293228 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.2442. Min Act: -0.1700
Data Index: 4902799 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.2442. Min Act: -0.1700
Data Index: 1708008 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.2442. Min Act: -0.1700
Data Index: 6287184 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.2130. Min Act: -0.1700
Data Index: 2647728 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.2442. Min Act: -0.1700
Data Index: 6787121 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.2130. Min Act: -0.1700
Data Index: 40728 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1817. Min Act: -0.1700
Data Index: 7860872 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1817. Min Act: -0.1700
Data Index: 2639056 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1505. Min Act: -0.1700
Data Index: 5669713 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1505. Min Act: -0.1700
Data Index: 5772522 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1505. Min Act: -0.1700
Data Index: 2154503 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1817. Min Act: -0.1700
Data Index: 8640557 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1192. Min Act: -0.1700
Data Index: 1605170 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19