Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0231. Min Range: -4.0231
Max Act: 4.0231. Min Act: -0.1700
Data Index: 1473104 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.9918. Min Act: -0.1700
Data Index: 3130915 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.9293. Min Act: -0.1700
Data Index: 6302993 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.8980. Min Act: -0.1700
Data Index: 3967941 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.8980. Min Act: -0.1700
Data Index: 3675657 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.8667. Min Act: -0.1700
Data Index: 7441408 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.8667. Min Act: -0.1700
Data Index: 7960274 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.8667. Min Act: -0.1700
Data Index: 1860113 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.8355. Min Act: -0.1700
Data Index: 2984814 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.8042. Min Act: -0.1700
Data Index: 8642150 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.8042. Min Act: -0.1700
Data Index: 7365404 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.8042. Min Act: -0.1700
Data Index: 3721875 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.7729. Min Act: -0.1700
Data Index: 5015381 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.7729. Min Act: -0.1700
Data Index: 3838224 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.7729. Min Act: -0.1700
Data Index: 7133451 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.7729. Min Act: -0.1700
Data Index: 4914973 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.7729. Min Act: -0.1700
Data Index: 3442639 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.7416. Min Act: -0.1700
Data Index: 3714130 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.7416. Min Act: -0.1700
Data Index: 1944966 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0231. Min Range: -4.0231
Max Act: 3.7416. Min Act: -0.1700
Data Index: 4603058 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19