Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1359. Min Range: -4.1359
Max Act: 4.1359. Min Act: -0.1700
Data Index: 5766293 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1359. Min Range: -4.1359
Max Act: 4.1046. Min Act: -0.1700
Data Index: 7254782 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.9483. Min Act: -0.1700
Data Index: 743802 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.9171. Min Act: -0.1700
Data Index: 5289145 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.9171. Min Act: -0.1700
Data Index: 2212079 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.9171. Min Act: -0.1700
Data Index: 6592265 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8858. Min Act: -0.1700
Data Index: 1973824 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8858. Min Act: -0.1700
Data Index: 5463815 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8545. Min Act: -0.1700
Data Index: 5509844 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8858. Min Act: -0.1700
Data Index: 4605811 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8233. Min Act: -0.1700
Data Index: 8068732 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8545. Min Act: -0.1700
Data Index: 3812592 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8545. Min Act: -0.1700
Data Index: 5213261 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8858. Min Act: -0.1700
Data Index: 4977426 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8858. Min Act: -0.1700
Data Index: 6451569 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8233. Min Act: -0.1700
Data Index: 40366 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8545. Min Act: -0.1700
Data Index: 743801 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8233. Min Act: -0.1700
Data Index: 3323790 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8545. Min Act: -0.1700
Data Index: 6280566 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1359. Min Range: -4.1359
Max Act: 3.8858. Min Act: -0.1700
Data Index: 101922 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19