Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 573 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.1595. Min Act: -0.1700
Data Index: 1589649 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.1282. Min Act: -0.1700
Data Index: 6576160 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0969. Min Act: -0.1700
Data Index: 8736741 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0657. Min Act: -0.1700
Data Index: 5566116 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0657. Min Act: -0.1700
Data Index: 366697 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0344. Min Act: -0.1700
Data Index: 3171315 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0344. Min Act: -0.1700
Data Index: 6576152 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0344. Min Act: -0.1700
Data Index: 3257174 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0344. Min Act: -0.1700
Data Index: 4336652 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0344. Min Act: -0.1700
Data Index: 4624661 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0657. Min Act: -0.1700
Data Index: 2831809 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0344. Min Act: -0.1700
Data Index: 5095149 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0344. Min Act: -0.1700
Data Index: 366708 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0344. Min Act: -0.1700
Data Index: 7329918 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0344. Min Act: -0.1700
Data Index: 2197045 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0344. Min Act: -0.1700
Data Index: 5185911 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0344. Min Act: -0.1700
Data Index: 1856939 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0032. Min Act: -0.1700
Data Index: 2863341 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0032. Min Act: -0.1700
Data Index: 2905213 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1595. Min Range: -4.1595
Max Act: 4.0032. Min Act: -0.1700
Data Index: 330790 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19