Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2478 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.8044. Min Act: -0.1700
Data Index: 3987098 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.7419. Min Act: -0.1700
Data Index: 3197937 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.5544. Min Act: -0.1700
Data Index: 8423125 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.4606. Min Act: -0.1700
Data Index: 164192 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.4606. Min Act: -0.1700
Data Index: 7941932 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.4606. Min Act: -0.1700
Data Index: 1559263 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.4294. Min Act: -0.1700
Data Index: 981389 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.4294. Min Act: -0.1700
Data Index: 8090850 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.4294. Min Act: -0.1700
Data Index: 169912 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.4294. Min Act: -0.1700
Data Index: 7423706 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.3981. Min Act: -0.1700
Data Index: 2715993 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.3981. Min Act: -0.1700
Data Index: 3014183 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.3981. Min Act: -0.1700
Data Index: 4139226 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.3981. Min Act: -0.1700
Data Index: 5923463 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.3669. Min Act: -0.1700
Data Index: 3525129 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.3356. Min Act: -0.1700
Data Index: 2972839 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.3356. Min Act: -0.1700
Data Index: 6105204 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.3356. Min Act: -0.1700
Data Index: 5186778 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.3356. Min Act: -0.1700
Data Index: 1562145 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8044. Min Range: -5.8044
Max Act: 5.3044. Min Act: -0.1700
Data Index: 2155120 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19