Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1966 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4449. Min Range: -11.4449
Max Act: 11.4449. Min Act: -0.1700
Data Index: 6093767 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4449. Min Range: -11.4449
Max Act: 11.0074. Min Act: -0.1700
Data Index: 1148580 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.7574. Min Act: -0.1700
Data Index: 2161601 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.5699. Min Act: -0.1700
Data Index: 6860794 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.3824. Min Act: -0.1700
Data Index: 5689910 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.3199. Min Act: -0.1700
Data Index: 1139511 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.3199. Min Act: -0.1700
Data Index: 2478247 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.2574. Min Act: -0.1700
Data Index: 1292387 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.2574. Min Act: -0.1700
Data Index: 8439956 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.1949. Min Act: -0.1700
Data Index: 5387126 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.1324. Min Act: -0.1700
Data Index: 6017412 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.1324. Min Act: -0.1700
Data Index: 7085434 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.0699. Min Act: -0.1700
Data Index: 114697 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.0699. Min Act: -0.1700
Data Index: 1494910 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.0699. Min Act: -0.1700
Data Index: 4037053 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.0074. Min Act: -0.1700
Data Index: 5289268 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.0074. Min Act: -0.1700
Data Index: 3671379 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.0074. Min Act: -0.1700
Data Index: 7288518 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.0074. Min Act: -0.1700
Data Index: 1795935 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4449. Min Range: -11.4449
Max Act: 10.0074. Min Act: -0.1700
Data Index: 2109991 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19