Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2937 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2677. Min Range: -10.2677
Max Act: 10.2677. Min Act: -0.1700
Data Index: 7470228 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2677. Min Range: -10.2677
Max Act: 10.2052. Min Act: -0.1700
Data Index: 5325535 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2677. Min Range: -10.2677
Max Act: 10.0802. Min Act: -0.1700
Data Index: 4061394 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.8927. Min Act: -0.1700
Data Index: 1953000 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.8302. Min Act: -0.1700
Data Index: 1430098 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.8302. Min Act: -0.1700
Data Index: 8221064 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.8302. Min Act: -0.1700
Data Index: 1488828 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.7677. Min Act: -0.1700
Data Index: 3412198 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.6427. Min Act: -0.1700
Data Index: 4837762 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.5802. Min Act: -0.1700
Data Index: 5957381 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.5802. Min Act: -0.1700
Data Index: 1152955 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.5802. Min Act: -0.1700
Data Index: 7820082 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.5802. Min Act: -0.1700
Data Index: 5139778 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.5177. Min Act: -0.1700
Data Index: 4372753 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.4552. Min Act: -0.1700
Data Index: 6696223 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.5177. Min Act: -0.1700
Data Index: 5326933 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.5177. Min Act: -0.1700
Data Index: 7192804 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.4552. Min Act: -0.1700
Data Index: 5634097 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.4552. Min Act: -0.1700
Data Index: 7391378 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2677. Min Range: -10.2677
Max Act: 9.4552. Min Act: -0.1700
Data Index: 1675896 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19