Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2911 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.5489. Min Act: -0.1700
Data Index: 5074471 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.4864. Min Act: -0.1700
Data Index: 8759563 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.4551. Min Act: -0.1700
Data Index: 5814412 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.3613. Min Act: -0.1700
Data Index: 5599140 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2676. Min Act: -0.1700
Data Index: 8488107 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2988. Min Act: -0.1700
Data Index: 1407859 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2988. Min Act: -0.1700
Data Index: 5897762 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2988. Min Act: -0.1700
Data Index: 8763892 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2988. Min Act: -0.1700
Data Index: 334446 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2676. Min Act: -0.1700
Data Index: 3677473 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2676. Min Act: -0.1700
Data Index: 311486 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2363. Min Act: -0.1700
Data Index: 6617657 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2363. Min Act: -0.1700
Data Index: 311475 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2051. Min Act: -0.1700
Data Index: 2236409 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2363. Min Act: -0.1700
Data Index: 7698848 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2051. Min Act: -0.1700
Data Index: 3527201 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2051. Min Act: -0.1700
Data Index: 4657048 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2051. Min Act: -0.1700
Data Index: 8759572 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2051. Min Act: -0.1700
Data Index: 3830090 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5489. Min Range: -4.5489
Max Act: 4.2363. Min Act: -0.1700
Data Index: 2639567 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19