Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.3884. Min Act: -0.1700
Data Index: 4743666 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.3721. Min Act: -0.1700
Data Index: 935460 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.3393. Min Act: -0.1700
Data Index: 8614465 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.3229. Min Act: -0.1700
Data Index: 5543993 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.3065. Min Act: -0.1700
Data Index: 4961158 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.3065. Min Act: -0.1700
Data Index: 2909979 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.2900. Min Act: -0.1700
Data Index: 5543994 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.2735. Min Act: -0.1700
Data Index: 6915538 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.2570. Min Act: -0.1700
Data Index: 5462146 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.2735. Min Act: -0.1700
Data Index: 5481071 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.2405. Min Act: -0.1700
Data Index: 2727728 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.2735. Min Act: -0.1700
Data Index: 3033018 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.2405. Min Act: -0.1700
Data Index: 2946066 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.2405. Min Act: -0.1700
Data Index: 3692075 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.2405. Min Act: -0.1700
Data Index: 8349302 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.2405. Min Act: -0.1700
Data Index: 2235087 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.2735. Min Act: -0.1700
Data Index: 5608535 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.1908. Min Act: -0.1700
Data Index: 5010569 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.2240. Min Act: -0.1700
Data Index: 961386 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3884. Min Range: -2.3884
Max Act: 2.2405. Min Act: -0.1700
Data Index: 4578392 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19