Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2255 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.4651. Min Act: -0.1700
Data Index: 7979735 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.4024. Min Act: -0.1700
Data Index: 2814742 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.3710. Min Act: -0.1700
Data Index: 3280803 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.3710. Min Act: -0.1700
Data Index: 2814744 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.3240. Min Act: -0.1700
Data Index: 8005866 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.3397. Min Act: -0.1700
Data Index: 3978162 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.3397. Min Act: -0.1700
Data Index: 3392657 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.3083. Min Act: -0.1700
Data Index: 3392656 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.3083. Min Act: -0.1700
Data Index: 3392653 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.2926. Min Act: -0.1700
Data Index: 6150335 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.3240. Min Act: -0.1700
Data Index: 4984922 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.2926. Min Act: -0.1700
Data Index: 1518268 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.2926. Min Act: -0.1700
Data Index: 1991137 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.3083. Min Act: -0.1700
Data Index: 6361820 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.3083. Min Act: -0.1700
Data Index: 4346293 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.2769. Min Act: -0.1700
Data Index: 2973207 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.2769. Min Act: -0.1700
Data Index: 7088162 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.2926. Min Act: -0.1700
Data Index: 5554283 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.2612. Min Act: -0.1700
Data Index: 663523 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4651. Min Range: -3.4651
Max Act: 3.2926. Min Act: -0.1700
Data Index: 8079740 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19