Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2800 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.8961. Min Act: -0.1700
Data Index: 2716248 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.8336. Min Act: -0.1700
Data Index: 8738907 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.8024. Min Act: -0.1700
Data Index: 5888712 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.8336. Min Act: -0.1700
Data Index: 2981176 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.7399. Min Act: -0.1700
Data Index: 5749599 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.7711. Min Act: -0.1700
Data Index: 2902117 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.7399. Min Act: -0.1700
Data Index: 8574821 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.7086. Min Act: -0.1700
Data Index: 5088094 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.7399. Min Act: -0.1700
Data Index: 8258031 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.7399. Min Act: -0.1700
Data Index: 5787022 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.7086. Min Act: -0.1700
Data Index: 337856 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.7086. Min Act: -0.1700
Data Index: 133494 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.7399. Min Act: -0.1700
Data Index: 867378 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.7399. Min Act: -0.1700
Data Index: 8368211 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.6774. Min Act: -0.1700
Data Index: 5012146 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.6774. Min Act: -0.1700
Data Index: 3224184 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.7086. Min Act: -0.1700
Data Index: 7337368 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.6149. Min Act: -0.1700
Data Index: 7718822 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.6461. Min Act: -0.1700
Data Index: 7873498 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8961. Min Range: -5.8961
Max Act: 5.6461. Min Act: -0.1700
Data Index: 1251660 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19