Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.5783. Min Act: -0.1700
Data Index: 6703248 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.3283. Min Act: -0.1700
Data Index: 4914786 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.2970. Min Act: -0.1700
Data Index: 1367535 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.2658. Min Act: -0.1700
Data Index: 4208187 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.2345. Min Act: -0.1700
Data Index: 3514563 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.2345. Min Act: -0.1700
Data Index: 1224637 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.2345. Min Act: -0.1700
Data Index: 1392929 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.2345. Min Act: -0.1700
Data Index: 203731 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.2345. Min Act: -0.1700
Data Index: 7259314 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.2345. Min Act: -0.1700
Data Index: 2126147 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.2033. Min Act: -0.1700
Data Index: 3443300 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.2033. Min Act: -0.1700
Data Index: 7061848 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.1720. Min Act: -0.1700
Data Index: 1799414 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.1720. Min Act: -0.1700
Data Index: 169871 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.1720. Min Act: -0.1700
Data Index: 7060965 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.1408. Min Act: -0.1700
Data Index: 8009477 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.1095. Min Act: -0.1700
Data Index: 1609968 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.1095. Min Act: -0.1700
Data Index: 2803522 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.1095. Min Act: -0.1700
Data Index: 2763425 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5783. Min Range: -6.5783
Max Act: 6.1095. Min Act: -0.1700
Data Index: 6703253 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19