Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3542 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.9862. Min Act: -0.1700
Data Index: 6776574 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.9862. Min Act: -0.1700
Data Index: 2213407 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.9516. Min Act: -0.1700
Data Index: 6776573 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.9172. Min Act: -0.1700
Data Index: 3714754 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.9172. Min Act: -0.1700
Data Index: 4879702 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.8321. Min Act: -0.1700
Data Index: 4282450 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.8321. Min Act: -0.1700
Data Index: 2210183 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.8152. Min Act: -0.1700
Data Index: 7754467 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.7984. Min Act: -0.1700
Data Index: 813742 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.8152. Min Act: -0.1700
Data Index: 7157274 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.7984. Min Act: -0.1700
Data Index: 7157275 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.7817. Min Act: -0.1700
Data Index: 6077430 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.7817. Min Act: -0.1700
Data Index: 6825289 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.7817. Min Act: -0.1700
Data Index: 274899 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.7817. Min Act: -0.1680
Data Index: 7607578 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.7817. Min Act: -0.1700
Data Index: 1596957 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.7651. Min Act: -0.1700
Data Index: 5643603 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.7651. Min Act: -0.1700
Data Index: 5607246 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.7651. Min Act: -0.1699
Data Index: 5619665 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9862. Min Range: -0.9862
Max Act: 0.7651. Min Act: -0.1700
Data Index: 1350089 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19