Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4461 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.4941. Min Act: -0.1700
Data Index: 6380847 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.3973. Min Act: -0.1700
Data Index: 608949 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.3797. Min Act: -0.1700
Data Index: 1138653 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.3885. Min Act: -0.1700
Data Index: 2998047 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.3709. Min Act: -0.1700
Data Index: 2770612 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.3180. Min Act: -0.1700
Data Index: 2407857 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.3003. Min Act: -0.1700
Data Index: 5702344 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.2915. Min Act: -0.1700
Data Index: 6888806 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.3003. Min Act: -0.1700
Data Index: 7022454 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.2915. Min Act: -0.1700
Data Index: 5352073 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.2827. Min Act: -0.1700
Data Index: 3802105 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.2915. Min Act: -0.1700
Data Index: 5735793 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.2739. Min Act: -0.1700
Data Index: 3815681 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.2739. Min Act: -0.1700
Data Index: 8486306 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.2650. Min Act: -0.1700
Data Index: 5964160 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.2650. Min Act: -0.1700
Data Index: 4865042 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.2650. Min Act: -0.1700
Data Index: 7002138 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.2650. Min Act: -0.1700
Data Index: 3448324 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.2562. Min Act: -0.1700
Data Index: 5112914 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4941. Min Range: -1.4941
Max Act: 1.2474. Min Act: -0.1700
Data Index: 3258069 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19