Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 734 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.6035. Min Act: -0.1700
Data Index: 1662605 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.5723. Min Act: -0.1700
Data Index: 184137 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.5098. Min Act: -0.1700
Data Index: 3195388 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.5723. Min Act: -0.1700
Data Index: 4295606 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.5098. Min Act: -0.1700
Data Index: 868015 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.5723. Min Act: -0.1700
Data Index: 4411615 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.5098. Min Act: -0.1700
Data Index: 4709620 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.4785. Min Act: -0.1700
Data Index: 3344056 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.4472. Min Act: -0.1700
Data Index: 3025699 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.4785. Min Act: -0.1700
Data Index: 5503775 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.4472. Min Act: -0.1700
Data Index: 5498851 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.4785. Min Act: -0.1700
Data Index: 6302238 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.4472. Min Act: -0.1700
Data Index: 5832564 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.4160. Min Act: -0.1700
Data Index: 3748994 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.3847. Min Act: -0.1700
Data Index: 6378874 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.3847. Min Act: -0.1700
Data Index: 849062 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.3222. Min Act: -0.1700
Data Index: 8469756 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.4160. Min Act: -0.1700
Data Index: 3052708 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.3535. Min Act: -0.1700
Data Index: 3883703 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6035. Min Range: -4.6035
Max Act: 4.3222. Min Act: -0.1700
Data Index: 6056437 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19