Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5061 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.8455. Min Act: -0.1700
Data Index: 2119696 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.7830. Min Act: -0.1700
Data Index: 4201945 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.5642. Min Act: -0.1700
Data Index: 8250556 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.5330. Min Act: -0.1700
Data Index: 743818 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.5017. Min Act: -0.1700
Data Index: 1319729 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.5017. Min Act: -0.1700
Data Index: 8428261 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.5017. Min Act: -0.1700
Data Index: 7393974 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.4705. Min Act: -0.1700
Data Index: 5826647 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.4705. Min Act: -0.1700
Data Index: 5921263 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.4705. Min Act: -0.1700
Data Index: 1386960 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.4392. Min Act: -0.1700
Data Index: 7046631 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.4080. Min Act: -0.1700
Data Index: 5191490 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.4392. Min Act: -0.1700
Data Index: 5048814 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.4392. Min Act: -0.1700
Data Index: 1515152 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.4080. Min Act: -0.1700
Data Index: 3357832 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.4080. Min Act: -0.1700
Data Index: 7802318 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.4080. Min Act: -0.1700
Data Index: 8237538 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.4080. Min Act: -0.1700
Data Index: 1938873 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.4080. Min Act: -0.1700
Data Index: 3756141 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8455. Min Range: -4.8455
Max Act: 4.4080. Min Act: -0.1700
Data Index: 5729383 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19