Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2650 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.9220. Min Act: -0.1700
Data Index: 5851017 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.6095. Min Act: -0.1700
Data Index: 6143211 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.4845. Min Act: -0.1700
Data Index: 4495877 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.4220. Min Act: -0.1700
Data Index: 1278067 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.4220. Min Act: -0.1700
Data Index: 1788255 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.4220. Min Act: -0.1700
Data Index: 1498826 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.2970. Min Act: -0.1700
Data Index: 7693491 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.2970. Min Act: -0.1700
Data Index: 6118069 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.2970. Min Act: -0.1700
Data Index: 7669736 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.2970. Min Act: -0.1700
Data Index: 1319394 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.2345. Min Act: -0.1700
Data Index: 4177839 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.2345. Min Act: -0.1700
Data Index: 3698198 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.1720. Min Act: -0.1700
Data Index: 7265930 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.1720. Min Act: -0.1700
Data Index: 4497347 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.1720. Min Act: -0.1700
Data Index: 2411321 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.1720. Min Act: -0.1700
Data Index: 6723318 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.1095. Min Act: -0.1700
Data Index: 4083817 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.1095. Min Act: -0.1700
Data Index: 15765 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.1095. Min Act: -0.1700
Data Index: 1779787 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9220. Min Range: -8.9220
Max Act: 8.1095. Min Act: -0.1700
Data Index: 4500340 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19