Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2831 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.7100. Min Act: -0.1700
Data Index: 3576097 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.7100. Min Act: -0.1700
Data Index: 5987614 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.5538. Min Act: -0.1700
Data Index: 7269239 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.5538. Min Act: -0.1700
Data Index: 8459161 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.5538. Min Act: -0.1700
Data Index: 4570567 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.5225. Min Act: -0.1700
Data Index: 3738976 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.4913. Min Act: -0.1700
Data Index: 7679917 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.4600. Min Act: -0.1700
Data Index: 304954 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.4600. Min Act: -0.1700
Data Index: 1815271 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.4288. Min Act: -0.1700
Data Index: 578749 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.4288. Min Act: -0.1700
Data Index: 5309628 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.3663. Min Act: -0.1700
Data Index: 5795658 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.3975. Min Act: -0.1700
Data Index: 5862713 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.3663. Min Act: -0.1700
Data Index: 2683362 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.3663. Min Act: -0.1700
Data Index: 3335312 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.3350. Min Act: -0.1700
Data Index: 2226216 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.3350. Min Act: -0.1700
Data Index: 3995667 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.3038. Min Act: -0.1700
Data Index: 6384953 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.3350. Min Act: -0.1700
Data Index: 77959 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.3038. Min Act: -0.1700
Data Index: 475805 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19