Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4239 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3946. Min Range: -8.3946
Max Act: 8.3946. Min Act: -0.1700
Data Index: 1536976 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3946. Min Range: -8.3946
Max Act: 8.2696. Min Act: -0.1700
Data Index: 6331436 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3946. Min Range: -8.3946
Max Act: 8.2071. Min Act: -0.1700
Data Index: 8359962 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3946. Min Range: -8.3946
Max Act: 8.1446. Min Act: -0.1700
Data Index: 6930335 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3946. Min Range: -8.3946
Max Act: 8.0821. Min Act: -0.1700
Data Index: 7593045 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3946. Min Range: -8.3946
Max Act: 8.0821. Min Act: -0.1700
Data Index: 3591805 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3946. Min Range: -8.3946
Max Act: 8.0821. Min Act: -0.1700
Data Index: 2158691 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3946. Min Range: -8.3946
Max Act: 8.0196. Min Act: -0.1700
Data Index: 1384792 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3946. Min Range: -8.3946
Max Act: 8.0196. Min Act: -0.1700
Data Index: 2429470 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3946. Min Range: -8.3946
Max Act: 8.0196. Min Act: -0.1700
Data Index: 3599099 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3946. Min Range: -8.3946
Max Act: 8.0196. Min Act: -0.1700
Data Index: 6255534 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3946. Min Range: -8.3946
Max Act: 7.9571. Min Act: -0.1700
Data Index: 4014330 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3946. Min Range: -8.3946
Max Act: 7.9571. Min Act: -0.1700
Data Index: 4564938 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3946. Min Range: -8.3946
Max Act: 7.9571. Min Act: -0.1700
Data Index: 8139004 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3946. Min Range: -8.3946
Max Act: 7.8946. Min Act: -0.1700
Data Index: 7665462 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3946. Min Range: -8.3946
Max Act: 7.8946. Min Act: -0.1700
Data Index: 4056408 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3946. Min Range: -8.3946
Max Act: 7.8946. Min Act: -0.1700
Data Index: 593084 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3946. Min Range: -8.3946
Max Act: 7.8321. Min Act: -0.1700
Data Index: 5201231 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3946. Min Range: -8.3946
Max Act: 7.8946. Min Act: -0.1700
Data Index: 5779534 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3946. Min Range: -8.3946
Max Act: 7.8321. Min Act: -0.1700
Data Index: 2145159 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19