Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5562 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1323. Min Range: -7.1323
Max Act: 7.1323. Min Act: -0.1700
Data Index: 2191797 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1323. Min Range: -7.1323
Max Act: 7.0386. Min Act: -0.1700
Data Index: 6269120 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1323. Min Range: -7.1323
Max Act: 7.0073. Min Act: -0.1700
Data Index: 4487231 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.8511. Min Act: -0.1700
Data Index: 2646703 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.7573. Min Act: -0.1700
Data Index: 7692106 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.7573. Min Act: -0.1700
Data Index: 3743708 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.7261. Min Act: -0.1700
Data Index: 5955223 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.7261. Min Act: -0.1700
Data Index: 7724800 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.6948. Min Act: -0.1700
Data Index: 4454948 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.6948. Min Act: -0.1700
Data Index: 3301273 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.6636. Min Act: -0.1700
Data Index: 1469731 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.6323. Min Act: -0.1700
Data Index: 8823358 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.6323. Min Act: -0.1700
Data Index: 655807 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.6323. Min Act: -0.1700
Data Index: 3537056 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.6636. Min Act: -0.1700
Data Index: 3053037 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.6636. Min Act: -0.1700
Data Index: 7231933 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.6323. Min Act: -0.1700
Data Index: 3038082 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.6011. Min Act: -0.1700
Data Index: 2227109 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.6011. Min Act: -0.1700
Data Index: 1358766 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1323. Min Range: -7.1323
Max Act: 6.6011. Min Act: -0.1700
Data Index: 4169857 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19