Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1670 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.7448. Min Act: -0.1700
Data Index: 295386 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.6979. Min Act: -0.1700
Data Index: 1492081 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.6666. Min Act: -0.1700
Data Index: 8574568 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.6197. Min Act: -0.1700
Data Index: 4249674 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.6040. Min Act: -0.1700
Data Index: 4994643 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.6040. Min Act: -0.1700
Data Index: 2220638 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.5884. Min Act: -0.1700
Data Index: 1572633 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.5884. Min Act: -0.1700
Data Index: 8754470 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.5571. Min Act: -0.1700
Data Index: 5879225 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.5414. Min Act: -0.1700
Data Index: 8158287 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.5101. Min Act: -0.1700
Data Index: 4174339 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.5414. Min Act: -0.1700
Data Index: 7214535 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.5414. Min Act: -0.1700
Data Index: 8229773 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.5101. Min Act: -0.1700
Data Index: 7565411 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.4944. Min Act: -0.1700
Data Index: 6705300 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.5101. Min Act: -0.1700
Data Index: 8197695 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.4788. Min Act: -0.1700
Data Index: 6155038 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.4631. Min Act: -0.1700
Data Index: 5766010 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.4788. Min Act: -0.1700
Data Index: 204639 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7448. Min Range: -3.7448
Max Act: 3.4944. Min Act: -0.1700
Data Index: 7207472 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19