Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1587 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.5208. Min Act: -0.1700
Data Index: 5328943 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.3581. Min Act: -0.1700
Data Index: 7119981 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.3744. Min Act: -0.1700
Data Index: 8826023 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.3088. Min Act: -0.1700
Data Index: 24387 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.3088. Min Act: -0.1700
Data Index: 7880346 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.3088. Min Act: -0.1700
Data Index: 3211488 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.2924. Min Act: -0.1700
Data Index: 2734227 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.2759. Min Act: -0.1700
Data Index: 3369021 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.2924. Min Act: -0.1700
Data Index: 4007643 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.2759. Min Act: -0.1700
Data Index: 350309 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.2594. Min Act: -0.1700
Data Index: 8831975 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.2759. Min Act: -0.1700
Data Index: 152819 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.2759. Min Act: -0.1700
Data Index: 233535 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.2924. Min Act: -0.1700
Data Index: 5062465 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.2263. Min Act: -0.1700
Data Index: 1878288 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.2429. Min Act: -0.1700
Data Index: 4970915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.2098. Min Act: -0.1700
Data Index: 5486561 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.2263. Min Act: -0.1700
Data Index: 1605005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.2098. Min Act: -0.1700
Data Index: 5498389 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5208. Min Range: -2.5208
Max Act: 2.1932. Min Act: -0.1700
Data Index: 6630182 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19