Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3603 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.8676. Min Act: -0.1700
Data Index: 3383625 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.7114. Min Act: -0.1700
Data Index: 1405788 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.5239. Min Act: -0.1700
Data Index: 348890 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.4926. Min Act: -0.1700
Data Index: 6719611 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.4301. Min Act: -0.1700
Data Index: 2248883 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.3051. Min Act: -0.1700
Data Index: 656384 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.2739. Min Act: -0.1700
Data Index: 7798851 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.2739. Min Act: -0.1700
Data Index: 2404476 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.2426. Min Act: -0.1700
Data Index: 579686 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.2114. Min Act: -0.1700
Data Index: 6167896 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.1801. Min Act: -0.1700
Data Index: 1566193 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.1801. Min Act: -0.1700
Data Index: 1356331 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.1801. Min Act: -0.1700
Data Index: 2405962 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.1801. Min Act: -0.1700
Data Index: 1864139 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.1801. Min Act: -0.1700
Data Index: 4175704 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.1489. Min Act: -0.1700
Data Index: 4758838 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.1489. Min Act: -0.1700
Data Index: 4479228 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.1489. Min Act: -0.1700
Data Index: 7195093 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.1489. Min Act: -0.1700
Data Index: 2543640 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8676. Min Range: -6.8676
Max Act: 6.1489. Min Act: -0.1700
Data Index: 7320904 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19