Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.5076. Min Act: -0.1700
Data Index: 6054134 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4988. Min Act: -0.1698
Data Index: 2561921 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4901. Min Act: -0.1700
Data Index: 4824133 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4901. Min Act: -0.1700
Data Index: 739475 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4988. Min Act: -0.1700
Data Index: 820758 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4725. Min Act: -0.1700
Data Index: 8726640 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4725. Min Act: -0.1696
Data Index: 839523 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4725. Min Act: -0.1700
Data Index: 1994166 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4637. Min Act: -0.1695
Data Index: 8726639 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4637. Min Act: -0.1700
Data Index: 2255541 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4373. Min Act: -0.1700
Data Index: 2995231 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4373. Min Act: -0.1700
Data Index: 6150347 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4285. Min Act: -0.1700
Data Index: 6837281 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4373. Min Act: -0.1700
Data Index: 1765494 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4285. Min Act: -0.1696
Data Index: 7336234 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4285. Min Act: -0.1700
Data Index: 6921679 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4461. Min Act: -0.1700
Data Index: 8755743 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4197. Min Act: -0.1694
Data Index: 1994165 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4285. Min Act: -0.1700
Data Index: 6321033 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5076. Min Range: -1.5076
Max Act: 1.4197. Min Act: -0.1699
Data Index: 2795161 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19