Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4042 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.7257. Min Act: -0.1700
Data Index: 4748674 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.6632. Min Act: -0.1700
Data Index: 2267019 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.5382. Min Act: -0.1700
Data Index: 2229661 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.4132. Min Act: -0.1700
Data Index: 3640389 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.3819. Min Act: -0.1700
Data Index: 3286155 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.3819. Min Act: -0.1700
Data Index: 252255 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.3819. Min Act: -0.1700
Data Index: 5060975 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.4132. Min Act: -0.1700
Data Index: 3805247 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.3507. Min Act: -0.1700
Data Index: 5558226 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.3194. Min Act: -0.1700
Data Index: 1322740 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.2882. Min Act: -0.1700
Data Index: 6685483 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.2569. Min Act: -0.1700
Data Index: 5177227 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.2569. Min Act: -0.1700
Data Index: 1523126 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.2569. Min Act: -0.1700
Data Index: 7512909 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.2569. Min Act: -0.1700
Data Index: 4579876 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.2882. Min Act: -0.1700
Data Index: 3359893 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.1944. Min Act: -0.1700
Data Index: 7483008 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.1632. Min Act: -0.1700
Data Index: 5247991 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.1632. Min Act: -0.1700
Data Index: 8096282 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7257. Min Range: -6.7257
Max Act: 6.1632. Min Act: -0.1700
Data Index: 5060169 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19