Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1905 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4956. Min Range: -6.4956
Max Act: 6.4956. Min Act: -0.1700
Data Index: 7653928 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4956. Min Range: -6.4956
Max Act: 6.4331. Min Act: -0.1700
Data Index: 2201132 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4956. Min Range: -6.4956
Max Act: 6.1206. Min Act: -0.1700
Data Index: 7729828 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.9956. Min Act: -0.1700
Data Index: 7459675 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.9643. Min Act: -0.1700
Data Index: 4103427 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.9331. Min Act: -0.1700
Data Index: 2013268 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.9331. Min Act: -0.1700
Data Index: 7339556 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.9331. Min Act: -0.1700
Data Index: 2087443 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.9331. Min Act: -0.1700
Data Index: 3200393 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.9331. Min Act: -0.1700
Data Index: 3092364 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.9331. Min Act: -0.1700
Data Index: 6512492 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.9018. Min Act: -0.1700
Data Index: 1282195 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.8706. Min Act: -0.1700
Data Index: 3983281 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.9018. Min Act: -0.1700
Data Index: 124973 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.9018. Min Act: -0.1700
Data Index: 3389926 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.8706. Min Act: -0.1700
Data Index: 5148149 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.8706. Min Act: -0.1700
Data Index: 7775082 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.8706. Min Act: -0.1700
Data Index: 3143251 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.8706. Min Act: -0.1700
Data Index: 43825 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4956. Min Range: -6.4956
Max Act: 5.8393. Min Act: -0.1700
Data Index: 2798358 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19