Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1297 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1885. Min Range: -7.1885
Max Act: 7.1885. Min Act: -0.1700
Data Index: 5614572 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1885. Min Range: -7.1885
Max Act: 7.1572. Min Act: -0.1700
Data Index: 7994404 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1885. Min Range: -7.1885
Max Act: 7.0635. Min Act: -0.1700
Data Index: 2275873 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.9385. Min Act: -0.1700
Data Index: 667394 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.9385. Min Act: -0.1700
Data Index: 3647518 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.9072. Min Act: -0.1700
Data Index: 5905282 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.8760. Min Act: -0.1700
Data Index: 2610919 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.8760. Min Act: -0.1700
Data Index: 3409075 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.8135. Min Act: -0.1700
Data Index: 3896450 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.7510. Min Act: -0.1700
Data Index: 3612305 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.6885. Min Act: -0.1700
Data Index: 7994403 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.6885. Min Act: -0.1700
Data Index: 2677402 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.6885. Min Act: -0.1700
Data Index: 3071571 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.6885. Min Act: -0.1700
Data Index: 2678450 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.6260. Min Act: -0.1700
Data Index: 1531241 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.6572. Min Act: -0.1700
Data Index: 7244569 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.6260. Min Act: -0.1700
Data Index: 1311831 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.5947. Min Act: -0.1700
Data Index: 3031143 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.5947. Min Act: -0.1700
Data Index: 785969 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1885. Min Range: -7.1885
Max Act: 6.5947. Min Act: -0.1700
Data Index: 7804854 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19