Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2728 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1087. Min Range: -4.1087
Max Act: 4.1087. Min Act: -0.1700
Data Index: 5768247 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1087. Min Range: -4.1087
Max Act: 4.0462. Min Act: -0.1700
Data Index: 4970165 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1087. Min Range: -4.1087
Max Act: 4.0462. Min Act: -0.1700
Data Index: 198450 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1087. Min Range: -4.1087
Max Act: 4.0150. Min Act: -0.1700
Data Index: 8305048 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1087. Min Range: -4.1087
Max Act: 4.0462. Min Act: -0.1700
Data Index: 3186953 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1087. Min Range: -4.1087
Max Act: 4.0150. Min Act: -0.1700
Data Index: 1899958 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1087. Min Range: -4.1087
Max Act: 4.0150. Min Act: -0.1700
Data Index: 3225729 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1087. Min Range: -4.1087
Max Act: 4.0150. Min Act: -0.1700
Data Index: 2750318 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1087. Min Range: -4.1087
Max Act: 3.9837. Min Act: -0.1700
Data Index: 7168806 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1087. Min Range: -4.1087
Max Act: 3.9837. Min Act: -0.1700
Data Index: 3727669 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1087. Min Range: -4.1087
Max Act: 3.9837. Min Act: -0.1700
Data Index: 4507681 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1087. Min Range: -4.1087
Max Act: 3.9837. Min Act: -0.1700
Data Index: 3051596 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1087. Min Range: -4.1087
Max Act: 3.9524. Min Act: -0.1700
Data Index: 3946686 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1087. Min Range: -4.1087
Max Act: 3.9524. Min Act: -0.1700
Data Index: 5105264 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1087. Min Range: -4.1087
Max Act: 3.9524. Min Act: -0.1700
Data Index: 911990 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1087. Min Range: -4.1087
Max Act: 3.9524. Min Act: -0.1700
Data Index: 8425602 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1087. Min Range: -4.1087
Max Act: 3.9212. Min Act: -0.1700
Data Index: 6591381 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1087. Min Range: -4.1087
Max Act: 3.9524. Min Act: -0.1700
Data Index: 5446069 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1087. Min Range: -4.1087
Max Act: 3.9212. Min Act: -0.1700
Data Index: 2128769 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1087. Min Range: -4.1087
Max Act: 3.9212. Min Act: -0.1700
Data Index: 5044994 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19