Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3120 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1141. Min Range: -7.1141
Max Act: 7.1141. Min Act: -0.1700
Data Index: 1358831 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1141. Min Range: -7.1141
Max Act: 7.1141. Min Act: -0.1700
Data Index: 7186746 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1141. Min Range: -7.1141
Max Act: 7.0204. Min Act: -0.1700
Data Index: 6255350 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.9891. Min Act: -0.1700
Data Index: 7199487 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.8954. Min Act: -0.1700
Data Index: 1868391 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.8641. Min Act: -0.1700
Data Index: 2069589 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.8954. Min Act: -0.1700
Data Index: 4984183 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.8641. Min Act: -0.1700
Data Index: 1619930 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.8329. Min Act: -0.1700
Data Index: 3319564 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.7704. Min Act: -0.1700
Data Index: 1058871 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.8016. Min Act: -0.1700
Data Index: 2745036 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.7704. Min Act: -0.1700
Data Index: 5750538 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.7391. Min Act: -0.1700
Data Index: 1625519 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.7704. Min Act: -0.1700
Data Index: 4545338 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.7391. Min Act: -0.1700
Data Index: 7159130 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.7704. Min Act: -0.1700
Data Index: 1765272 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.7704. Min Act: -0.1700
Data Index: 3927912 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.7391. Min Act: -0.1700
Data Index: 62213 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.7391. Min Act: -0.1700
Data Index: 3092967 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1141. Min Range: -7.1141
Max Act: 6.7079. Min Act: -0.1700
Data Index: 2308899 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19