Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.5811. Min Act: -0.1700
Data Index: 3369251 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.5499. Min Act: -0.1700
Data Index: 7863182 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.5186. Min Act: -0.1700
Data Index: 8537727 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.5186. Min Act: -0.1700
Data Index: 598794 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.5186. Min Act: -0.1700
Data Index: 6933726 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4874. Min Act: -0.1700
Data Index: 3544322 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4874. Min Act: -0.1700
Data Index: 2716261 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4874. Min Act: -0.1700
Data Index: 2907938 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4874. Min Act: -0.1700
Data Index: 4109619 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4874. Min Act: -0.1700
Data Index: 5070160 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4874. Min Act: -0.1700
Data Index: 4957362 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4874. Min Act: -0.1700
Data Index: 4399885 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4561. Min Act: -0.1700
Data Index: 8553610 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4561. Min Act: -0.1700
Data Index: 7536134 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4561. Min Act: -0.1700
Data Index: 5613118 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4249. Min Act: -0.1700
Data Index: 7467215 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4249. Min Act: -0.1700
Data Index: 16058 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4249. Min Act: -0.1700
Data Index: 6357308 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4249. Min Act: -0.1700
Data Index: 5926575 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5811. Min Range: -4.5811
Max Act: 4.4249. Min Act: -0.1700
Data Index: 3607206 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19