Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2084 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.9049. Min Act: -0.1700
Data Index: 4004002 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.9049. Min Act: -0.1700
Data Index: 435562 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.8736. Min Act: -0.1700
Data Index: 6737754 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.7799. Min Act: -0.1700
Data Index: 2353593 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.7174. Min Act: -0.1700
Data Index: 5060268 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.6549. Min Act: -0.1700
Data Index: 2894045 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.6549. Min Act: -0.1700
Data Index: 3622095 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.6549. Min Act: -0.1700
Data Index: 885918 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.6549. Min Act: -0.1700
Data Index: 5124117 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.6549. Min Act: -0.1700
Data Index: 7532241 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.6549. Min Act: -0.1700
Data Index: 6100214 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.6549. Min Act: -0.1700
Data Index: 7285249 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.6236. Min Act: -0.1700
Data Index: 2558473 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.6236. Min Act: -0.1700
Data Index: 3140239 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.6236. Min Act: -0.1700
Data Index: 5896977 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.5924. Min Act: -0.1700
Data Index: 7113889 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.5924. Min Act: -0.1700
Data Index: 7048179 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.5924. Min Act: -0.1700
Data Index: 5602447 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.5611. Min Act: -0.1699
Data Index: 2346084 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9049. Min Range: -6.9049
Max Act: 6.5611. Min Act: -0.1700
Data Index: 529632 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19