Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 711 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.2033. Min Act: -0.1700
Data Index: 2393924 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.2345. Min Act: -0.1700
Data Index: 2065587 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.1408. Min Act: -0.1700
Data Index: 210755 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.1408. Min Act: -0.1700
Data Index: 7178541 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.1408. Min Act: -0.1700
Data Index: 4351957 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.1095. Min Act: -0.1700
Data Index: 4531316 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.1408. Min Act: -0.1700
Data Index: 2825808 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.1095. Min Act: -0.1700
Data Index: 1217743 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.1095. Min Act: -0.1700
Data Index: 634521 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.0783. Min Act: -0.1700
Data Index: 1991052 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.0783. Min Act: -0.1700
Data Index: 4336111 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.0783. Min Act: -0.1700
Data Index: 775678 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.0783. Min Act: -0.1700
Data Index: 5071972 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.0470. Min Act: -0.1700
Data Index: 1619918 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.0470. Min Act: -0.1700
Data Index: 2070594 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.0470. Min Act: -0.1700
Data Index: 16066 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.0470. Min Act: -0.1700
Data Index: 8200551 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.0158. Min Act: -0.1700
Data Index: 6971050 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.0158. Min Act: -0.1700
Data Index: 8654242 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2345. Min Range: -5.2345
Max Act: 5.0158. Min Act: -0.1700
Data Index: 1030172 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19