Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4477 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.4357. Min Act: -0.1700
Data Index: 2476353 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.2482. Min Act: -0.1700
Data Index: 2117113 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.2169. Min Act: -0.1700
Data Index: 356166 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.1544. Min Act: -0.1700
Data Index: 2298197 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.1544. Min Act: -0.1700
Data Index: 7659097 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.1544. Min Act: -0.1700
Data Index: 356170 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.1232. Min Act: -0.1700
Data Index: 2298200 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.0919. Min Act: -0.1700
Data Index: 2220166 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.0607. Min Act: -0.1700
Data Index: 1257250 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.0607. Min Act: -0.1700
Data Index: 2862139 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.0607. Min Act: -0.1700
Data Index: 2491539 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.0919. Min Act: -0.1700
Data Index: 3749629 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.0294. Min Act: -0.1700
Data Index: 2298199 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.0294. Min Act: -0.1700
Data Index: 3119592 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4357. Min Range: -4.4357
Max Act: 4.0294. Min Act: -0.1700
Data Index: 2095328 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4357. Min Range: -4.4357
Max Act: 3.9981. Min Act: -0.1700
Data Index: 4381008 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4357. Min Range: -4.4357
Max Act: 3.9981. Min Act: -0.1700
Data Index: 2117114 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4357. Min Range: -4.4357
Max Act: 3.9981. Min Act: -0.1700
Data Index: 2862140 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4357. Min Range: -4.4357
Max Act: 3.9669. Min Act: -0.1700
Data Index: 2117120 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4357. Min Range: -4.4357
Max Act: 3.9669. Min Act: -0.1700
Data Index: 29850 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19