Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4154 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.3958. Min Act: -0.1700
Data Index: 2151946 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.3646. Min Act: -0.1700
Data Index: 3272106 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.3646. Min Act: -0.1700
Data Index: 7625028 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.3646. Min Act: -0.1700
Data Index: 6929296 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.3646. Min Act: -0.1700
Data Index: 2403760 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.3333. Min Act: -0.1700
Data Index: 3090614 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.3021. Min Act: -0.1700
Data Index: 3164960 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.2708. Min Act: -0.1700
Data Index: 3030718 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.2708. Min Act: -0.1700
Data Index: 6793705 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.2708. Min Act: -0.1700
Data Index: 6783339 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.2396. Min Act: -0.1700
Data Index: 5411888 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.2708. Min Act: -0.1700
Data Index: 8800540 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.2396. Min Act: -0.1700
Data Index: 5896092 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.2083. Min Act: -0.1700
Data Index: 5869754 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.2083. Min Act: -0.1700
Data Index: 1761109 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.2083. Min Act: -0.1700
Data Index: 6118606 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.2083. Min Act: -0.1700
Data Index: 7920086 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.2083. Min Act: -0.1700
Data Index: 3900047 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.2083. Min Act: -0.1700
Data Index: 1255046 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3958. Min Range: -5.3958
Max Act: 5.1771. Min Act: -0.1700
Data Index: 5214974 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19