Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3461 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.5019. Min Act: -0.1700
Data Index: 7315754 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.3143. Min Act: -0.1700
Data Index: 3069866 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.3768. Min Act: -0.1700
Data Index: 7328136 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.3143. Min Act: -0.1700
Data Index: 5484270 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.3143. Min Act: -0.1700
Data Index: 2005233 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.3143. Min Act: -0.1700
Data Index: 7816702 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2831. Min Act: -0.1700
Data Index: 8093857 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2831. Min Act: -0.1700
Data Index: 5579395 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2518. Min Act: -0.1700
Data Index: 2813107 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2518. Min Act: -0.1700
Data Index: 5167378 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2206. Min Act: -0.1700
Data Index: 3601501 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2206. Min Act: -0.1700
Data Index: 2472442 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2206. Min Act: -0.1700
Data Index: 3491909 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2206. Min Act: -0.1700
Data Index: 8711155 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2518. Min Act: -0.1700
Data Index: 5445884 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2206. Min Act: -0.1700
Data Index: 4350728 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1893. Min Act: -0.1700
Data Index: 2741211 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1893. Min Act: -0.1700
Data Index: 1076167 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1581. Min Act: -0.1700
Data Index: 3996927 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1581. Min Act: -0.1700
Data Index: 6985270 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19