Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3871 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.5937. Min Act: -0.1700
Data Index: 3838118 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.4999. Min Act: -0.1700
Data Index: 393424 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.4999. Min Act: -0.1700
Data Index: 2723493 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.4686. Min Act: -0.1700
Data Index: 5258760 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.4686. Min Act: -0.1700
Data Index: 1770100 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.4374. Min Act: -0.1700
Data Index: 997934 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.4686. Min Act: -0.1700
Data Index: 5718428 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.4061. Min Act: -0.1700
Data Index: 4860910 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.4061. Min Act: -0.1700
Data Index: 6616350 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.3749. Min Act: -0.1700
Data Index: 1116302 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.3749. Min Act: -0.1700
Data Index: 8360725 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.3749. Min Act: -0.1700
Data Index: 3813787 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.4061. Min Act: -0.1700
Data Index: 3660868 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.3749. Min Act: -0.1700
Data Index: 137936 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.4061. Min Act: -0.1700
Data Index: 6616355 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.3749. Min Act: -0.1700
Data Index: 5555842 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.3124. Min Act: -0.1700
Data Index: 3740190 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.3436. Min Act: -0.1700
Data Index: 7929158 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.3436. Min Act: -0.1700
Data Index: 7827231 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5937. Min Range: -4.5937
Max Act: 4.3124. Min Act: -0.1700
Data Index: 3813783 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19