Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1620 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.9845. Min Act: -0.1700
Data Index: 5293080 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.9220. Min Act: -0.1700
Data Index: 4686465 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.7970. Min Act: -0.1700
Data Index: 4379875 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.7970. Min Act: -0.1700
Data Index: 8374392 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.7657. Min Act: -0.1700
Data Index: 6824535 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.7345. Min Act: -0.1700
Data Index: 6396106 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.7345. Min Act: -0.1700
Data Index: 811683 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.7345. Min Act: -0.1700
Data Index: 8385574 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.6720. Min Act: -0.1700
Data Index: 416799 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.7032. Min Act: -0.1700
Data Index: 5072042 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.6720. Min Act: -0.1700
Data Index: 8072084 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.6407. Min Act: -0.1700
Data Index: 8536349 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.6407. Min Act: -0.1700
Data Index: 4635811 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.6720. Min Act: -0.1700
Data Index: 6013257 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.6407. Min Act: -0.1700
Data Index: 3456437 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.5782. Min Act: -0.1700
Data Index: 8542820 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.6095. Min Act: -0.1700
Data Index: 4212365 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.5470. Min Act: -0.1700
Data Index: 2073698 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.5470. Min Act: -0.1700
Data Index: 5635403 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9845. Min Range: -5.9845
Max Act: 5.6095. Min Act: -0.1700
Data Index: 5434683 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19