Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2405 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.7117. Min Act: -0.1700
Data Index: 5744384 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.6476. Min Act: -0.1700
Data Index: 2297034 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.6316. Min Act: -0.1700
Data Index: 5135115 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.6155. Min Act: -0.1700
Data Index: 5182642 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.5672. Min Act: -0.1700
Data Index: 8009193 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.5672. Min Act: -0.1700
Data Index: 3662517 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.5349. Min Act: -0.1700
Data Index: 343609 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.5187. Min Act: -0.1700
Data Index: 1893240 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.5349. Min Act: -0.1700
Data Index: 369441 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.4538. Min Act: -0.1700
Data Index: 4298664 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.4701. Min Act: -0.1700
Data Index: 2791953 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.4376. Min Act: -0.1700
Data Index: 6208902 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.4538. Min Act: -0.1700
Data Index: 2618037 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.4538. Min Act: -0.1700
Data Index: 2038802 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.4701. Min Act: -0.1700
Data Index: 4447048 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.4701. Min Act: -0.1700
Data Index: 105412 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.4538. Min Act: -0.1700
Data Index: 7370625 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.4376. Min Act: -0.1700
Data Index: 1703177 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.4538. Min Act: -0.1700
Data Index: 4797226 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7117. Min Range: -2.7117
Max Act: 2.4376. Min Act: -0.1700
Data Index: 1232630 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19