Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3723 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0702. Min Range: -4.0702
Max Act: 4.0702. Min Act: -0.1700
Data Index: 6625985 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.9765. Min Act: -0.1700
Data Index: 4808275 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.9765. Min Act: -0.1700
Data Index: 1888918 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.9139. Min Act: -0.1700
Data Index: 8321424 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.8827. Min Act: -0.1700
Data Index: 6103279 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.8514. Min Act: -0.1700
Data Index: 5394759 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.8201. Min Act: -0.1700
Data Index: 2119880 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.8201. Min Act: -0.1700
Data Index: 6688706 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.8201. Min Act: -0.1700
Data Index: 1614125 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.7888. Min Act: -0.1700
Data Index: 3834640 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.7888. Min Act: -0.1700
Data Index: 6061969 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.7263. Min Act: -0.1700
Data Index: 8042310 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.6950. Min Act: -0.1700
Data Index: 526399 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.7263. Min Act: -0.1700
Data Index: 423515 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.7263. Min Act: -0.1700
Data Index: 5449103 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.6950. Min Act: -0.1700
Data Index: 2140917 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.6950. Min Act: -0.1700
Data Index: 1080925 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.6950. Min Act: -0.1700
Data Index: 3471316 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.6950. Min Act: -0.1700
Data Index: 6378881 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0702. Min Range: -4.0702
Max Act: 3.6950. Min Act: -0.1700
Data Index: 5820563 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19