Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 345 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.3155. Min Act: -0.1700
Data Index: 5538770 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2842. Min Act: -0.1700
Data Index: 1582780 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2842. Min Act: -0.1700
Data Index: 1842055 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2530. Min Act: -0.1700
Data Index: 3449428 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2530. Min Act: -0.1700
Data Index: 3028652 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2530. Min Act: -0.1700
Data Index: 5510648 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2530. Min Act: -0.1700
Data Index: 3183050 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2530. Min Act: -0.1700
Data Index: 340075 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2530. Min Act: -0.1700
Data Index: 4398967 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2530. Min Act: -0.1700
Data Index: 6615352 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2530. Min Act: -0.1700
Data Index: 7720433 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2530. Min Act: -0.1700
Data Index: 3103591 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2530. Min Act: -0.1700
Data Index: 1842525 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2530. Min Act: -0.1700
Data Index: 107366 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.2530. Min Act: -0.1700
Data Index: 7418385 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.1905. Min Act: -0.1700
Data Index: 3690224 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.0967. Min Act: -0.1700
Data Index: 1434748 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.0967. Min Act: -0.1700
Data Index: 90764 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.0967. Min Act: -0.1700
Data Index: 6621115 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3155. Min Range: -5.3155
Max Act: 5.0967. Min Act: -0.1700
Data Index: 7170418 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19