Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 849 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.6514. Min Act: -0.1700
Data Index: 8224116 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.6514. Min Act: -0.1700
Data Index: 6802541 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.6514. Min Act: -0.1700
Data Index: 6202182 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5889. Min Act: -0.1700
Data Index: 8473394 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5889. Min Act: -0.1700
Data Index: 4431142 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 5896833 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 3108259 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 3276310 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 4431143 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1699
Data Index: 1540442 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 1604821 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 8487598 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5264. Min Act: -0.1700
Data Index: 1982770 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5264. Min Act: -0.1700
Data Index: 7072915 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5264. Min Act: -0.1700
Data Index: 2465110 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5264. Min Act: -0.1700
Data Index: 1292384 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5264. Min Act: -0.1700
Data Index: 1886216 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5264. Min Act: -0.1700
Data Index: 4037587 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.4639. Min Act: -0.1700
Data Index: 635739 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.4639. Min Act: -0.1700
Data Index: 1802850 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19