Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2878 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2059. Min Range: -6.2059
Max Act: 6.2059. Min Act: -0.1700
Data Index: 1393042 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2059. Min Range: -6.2059
Max Act: 6.1434. Min Act: -0.1700
Data Index: 8304071 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2059. Min Range: -6.2059
Max Act: 6.1122. Min Act: -0.1700
Data Index: 3872539 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2059. Min Range: -6.2059
Max Act: 6.0497. Min Act: -0.1700
Data Index: 3370171 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2059. Min Range: -6.2059
Max Act: 6.0184. Min Act: -0.1700
Data Index: 3453980 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2059. Min Range: -6.2059
Max Act: 6.0184. Min Act: -0.1700
Data Index: 6591874 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.9247. Min Act: -0.1700
Data Index: 3004077 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.9559. Min Act: -0.1700
Data Index: 4427499 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.9559. Min Act: -0.1700
Data Index: 4376780 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.9559. Min Act: -0.1700
Data Index: 4348446 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.9247. Min Act: -0.1700
Data Index: 5998284 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.9247. Min Act: -0.1700
Data Index: 1359528 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.9247. Min Act: -0.1700
Data Index: 7529983 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.8934. Min Act: -0.1700
Data Index: 4769026 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.8934. Min Act: -0.1700
Data Index: 5564305 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.8934. Min Act: -0.1700
Data Index: 5524039 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.8622. Min Act: -0.1700
Data Index: 8413339 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.8622. Min Act: -0.1700
Data Index: 3917430 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.8622. Min Act: -0.1700
Data Index: 3157253 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2059. Min Range: -6.2059
Max Act: 5.7997. Min Act: -0.1700
Data Index: 3256509 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19