Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1625 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.4730. Min Act: -0.1700
Data Index: 349610 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.2855. Min Act: -0.1700
Data Index: 3102783 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.2855. Min Act: -0.1700
Data Index: 6167220 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.2855. Min Act: -0.1700
Data Index: 7441181 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.2542. Min Act: -0.1700
Data Index: 8423274 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.1917. Min Act: -0.1700
Data Index: 7162322 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.1605. Min Act: -0.1700
Data Index: 6430881 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.0980. Min Act: -0.1700
Data Index: 8302797 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.0980. Min Act: -0.1700
Data Index: 7474283 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.0980. Min Act: -0.1700
Data Index: 6311517 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.0980. Min Act: -0.1700
Data Index: 926438 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.0980. Min Act: -0.1700
Data Index: 3733452 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.0667. Min Act: -0.1700
Data Index: 4310208 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.0355. Min Act: -0.1700
Data Index: 4608270 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.0355. Min Act: -0.1700
Data Index: 1739146 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.0042. Min Act: -0.1700
Data Index: 6354259 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4730. Min Range: -5.4730
Max Act: 4.9730. Min Act: -0.1700
Data Index: 3069067 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.0042. Min Act: -0.1700
Data Index: 1708145 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.0042. Min Act: -0.1700
Data Index: 5081980 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4730. Min Range: -5.4730
Max Act: 5.0042. Min Act: -0.1700
Data Index: 1222528 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19