Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 153 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.5935. Min Act: -0.1700
Data Index: 4278563 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.5622. Min Act: -0.1700
Data Index: 3294139 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.4997. Min Act: -0.1700
Data Index: 773546 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.4685. Min Act: -0.1700
Data Index: 2451960 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.3747. Min Act: -0.1700
Data Index: 3814270 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.3122. Min Act: -0.1700
Data Index: 7529380 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.3435. Min Act: -0.1700
Data Index: 7860421 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.3747. Min Act: -0.1700
Data Index: 3971607 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.3435. Min Act: -0.1700
Data Index: 1091422 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.3435. Min Act: -0.1700
Data Index: 1654702 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.3435. Min Act: -0.1700
Data Index: 6665266 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.3747. Min Act: -0.1700
Data Index: 2494108 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.3122. Min Act: -0.1700
Data Index: 1238032 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.3122. Min Act: -0.1700
Data Index: 8524737 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.3122. Min Act: -0.1700
Data Index: 5611945 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.2497. Min Act: -0.1700
Data Index: 1083886 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.2497. Min Act: -0.1700
Data Index: 392741 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.2497. Min Act: -0.1700
Data Index: 2140677 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.1872. Min Act: -0.1700
Data Index: 7205176 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5935. Min Range: -4.5935
Max Act: 4.2497. Min Act: -0.1700
Data Index: 1052789 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19