Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.7021. Min Act: -0.1700
Data Index: 8195459 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.6083. Min Act: -0.1700
Data Index: 5957976 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.5146. Min Act: -0.1700
Data Index: 5515480 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.4208. Min Act: -0.1700
Data Index: 675497 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.4208. Min Act: -0.1700
Data Index: 1270987 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.3583. Min Act: -0.1700
Data Index: 1506070 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.3583. Min Act: -0.1700
Data Index: 7883196 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.3271. Min Act: -0.1700
Data Index: 7405025 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.2958. Min Act: -0.1700
Data Index: 5330379 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.2646. Min Act: -0.1700
Data Index: 432696 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.2646. Min Act: -0.1700
Data Index: 934371 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.2333. Min Act: -0.1700
Data Index: 4363988 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.2021. Min Act: -0.1700
Data Index: 6511399 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.2021. Min Act: -0.1700
Data Index: 7071920 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.2021. Min Act: -0.1700
Data Index: 6796707 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.1708. Min Act: -0.1700
Data Index: 5251107 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.1708. Min Act: -0.1700
Data Index: 3788517 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.1708. Min Act: -0.1700
Data Index: 3582267 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.1083. Min Act: -0.1700
Data Index: 2386114 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7021. Min Range: -6.7021
Max Act: 6.1396. Min Act: -0.1700
Data Index: 2023138 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19