Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4825 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2159. Min Range: -5.2159
Max Act: 5.2159. Min Act: -0.1700
Data Index: 6190509 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2159. Min Range: -5.2159
Max Act: 5.1221. Min Act: -0.1700
Data Index: 7594954 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.9346. Min Act: -0.1700
Data Index: 522305 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.9659. Min Act: -0.1700
Data Index: 6490151 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.9659. Min Act: -0.1700
Data Index: 3314936 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.9659. Min Act: -0.1700
Data Index: 3351716 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.9034. Min Act: -0.1700
Data Index: 4601844 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.9034. Min Act: -0.1700
Data Index: 4851175 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.8721. Min Act: -0.1700
Data Index: 5841486 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.9034. Min Act: -0.1700
Data Index: 454071 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.8721. Min Act: -0.1700
Data Index: 2219888 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.8721. Min Act: -0.1700
Data Index: 6501146 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.8721. Min Act: -0.1700
Data Index: 8372176 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.8721. Min Act: -0.1700
Data Index: 7768547 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.8721. Min Act: -0.1700
Data Index: 6919775 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.8721. Min Act: -0.1700
Data Index: 3965212 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.8721. Min Act: -0.1700
Data Index: 7837632 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.8409. Min Act: -0.1700
Data Index: 1197928 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.8096. Min Act: -0.1700
Data Index: 5910372 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2159. Min Range: -5.2159
Max Act: 4.8096. Min Act: -0.1700
Data Index: 4555982 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19