Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.2399. Min Act: -0.1700
Data Index: 1238762 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.0836. Min Act: -0.1700
Data Index: 3339715 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.0836. Min Act: -0.1700
Data Index: 132285 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.0836. Min Act: -0.1700
Data Index: 3372890 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.0523. Min Act: -0.1700
Data Index: 4218708 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.0523. Min Act: -0.1700
Data Index: 400498 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9898. Min Act: -0.1700
Data Index: 5958957 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.0211. Min Act: -0.1700
Data Index: 7132211 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9898. Min Act: -0.1700
Data Index: 1234714 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9898. Min Act: -0.1700
Data Index: 2998797 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9898. Min Act: -0.1700
Data Index: 4631432 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9585. Min Act: -0.1700
Data Index: 945710 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9585. Min Act: -0.1700
Data Index: 2982204 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9273. Min Act: -0.1700
Data Index: 1652813 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9585. Min Act: -0.1700
Data Index: 246985 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9273. Min Act: -0.1700
Data Index: 5381777 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9273. Min Act: -0.1700
Data Index: 6336028 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.8960. Min Act: -0.1700
Data Index: 5672927 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9273. Min Act: -0.1700
Data Index: 7685647 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9273. Min Act: -0.1700
Data Index: 7961436 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19