Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.1813. Min Act: -0.1698
Data Index: 6642355 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.1500. Min Act: -0.1700
Data Index: 4985483 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.1188. Min Act: -0.1700
Data Index: 1413442 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.1188. Min Act: -0.1700
Data Index: 2452141 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0875. Min Act: -0.1700
Data Index: 8286426 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0563. Min Act: -0.1700
Data Index: 944258 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0875. Min Act: -0.1700
Data Index: 1558142 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0250. Min Act: -0.1700
Data Index: 5378211 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0563. Min Act: -0.1700
Data Index: 695820 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0563. Min Act: -0.1700
Data Index: 3740513 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0563. Min Act: -0.1700
Data Index: 3639138 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0250. Min Act: -0.1700
Data Index: 167871 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0563. Min Act: -0.1700
Data Index: 3196392 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0250. Min Act: -0.1700
Data Index: 5623957 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0563. Min Act: -0.1700
Data Index: 757261 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0250. Min Act: -0.1700
Data Index: 5741019 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0250. Min Act: -0.1700
Data Index: 6298093 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0250. Min Act: -0.1700
Data Index: 2104358 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0250. Min Act: -0.1700
Data Index: 937599 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1813. Min Range: -6.1813
Max Act: 6.0250. Min Act: -0.1700
Data Index: 6526619 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19