Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3830 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.8367. Min Act: -0.1699
Data Index: 5677308 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7766. Min Act: -0.1700
Data Index: 8790930 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7679. Min Act: -0.1700
Data Index: 410158 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7593. Min Act: -0.1691
Data Index: 3231679 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7593. Min Act: -0.1700
Data Index: 4562736 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7593. Min Act: -0.1700
Data Index: 5335150 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7507. Min Act: -0.1700
Data Index: 6973954 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7507. Min Act: -0.1673
Data Index: 5797489 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7507. Min Act: -0.1671
Data Index: 7280965 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7420. Min Act: -0.1584
Data Index: 6544135 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7420. Min Act: -0.1699
Data Index: 8656900 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7420. Min Act: -0.1700
Data Index: 7805892 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7420. Min Act: -0.1691
Data Index: 4916606 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7334. Min Act: -0.1700
Data Index: 5930466 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7593. Min Act: -0.1630
Data Index: 2146598 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7334. Min Act: -0.1700
Data Index: 5363536 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7507. Min Act: -0.1593
Data Index: 4075676 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7247. Min Act: -0.1695
Data Index: 6829417 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7334. Min Act: -0.1700
Data Index: 3995530 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8367. Min Range: -1.8367
Max Act: 1.7334. Min Act: -0.1667
Data Index: 1573228 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19