Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2300 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1948. Min Range: -6.1948
Max Act: 6.1323. Min Act: -0.1700
Data Index: 6294900 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1948. Min Range: -6.1948
Max Act: 6.1948. Min Act: -0.1700
Data Index: 7129196 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1948. Min Range: -6.1948
Max Act: 6.1011. Min Act: -0.1700
Data Index: 8444916 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.9761. Min Act: -0.1700
Data Index: 8549841 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.9761. Min Act: -0.1700
Data Index: 758084 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.9448. Min Act: -0.1700
Data Index: 6996787 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.8823. Min Act: -0.1700
Data Index: 7621085 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.8511. Min Act: -0.1700
Data Index: 411289 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.8198. Min Act: -0.1700
Data Index: 895673 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.8511. Min Act: -0.1700
Data Index: 3882844 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.8511. Min Act: -0.1700
Data Index: 72144 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.8198. Min Act: -0.1700
Data Index: 5326225 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.7886. Min Act: -0.1700
Data Index: 2543576 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.8198. Min Act: -0.1700
Data Index: 6833580 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.7886. Min Act: -0.1700
Data Index: 2006639 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.8198. Min Act: -0.1700
Data Index: 246995 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.7886. Min Act: -0.1700
Data Index: 976758 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.7886. Min Act: -0.1700
Data Index: 7018397 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.7886. Min Act: -0.1700
Data Index: 6204928 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1948. Min Range: -6.1948
Max Act: 5.7886. Min Act: -0.1700
Data Index: 510834 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19