Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 60 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4986. Min Range: -6.4986
Max Act: 6.4986. Min Act: -0.1700
Data Index: 4950492 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4986. Min Range: -6.4986
Max Act: 6.4674. Min Act: -0.1700
Data Index: 3576878 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4986. Min Range: -6.4986
Max Act: 6.2799. Min Act: -0.1700
Data Index: 8767996 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4986. Min Range: -6.4986
Max Act: 6.2174. Min Act: -0.1700
Data Index: 3618019 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4986. Min Range: -6.4986
Max Act: 6.1549. Min Act: -0.1700
Data Index: 1842410 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4986. Min Range: -6.4986
Max Act: 6.1236. Min Act: -0.1700
Data Index: 8559025 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4986. Min Range: -6.4986
Max Act: 6.1236. Min Act: -0.1700
Data Index: 3719660 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4986. Min Range: -6.4986
Max Act: 6.0924. Min Act: -0.1700
Data Index: 6992914 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4986. Min Range: -6.4986
Max Act: 6.0924. Min Act: -0.1700
Data Index: 8013869 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4986. Min Range: -6.4986
Max Act: 6.0924. Min Act: -0.1700
Data Index: 3118709 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4986. Min Range: -6.4986
Max Act: 6.0299. Min Act: -0.1700
Data Index: 5116665 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4986. Min Range: -6.4986
Max Act: 6.0611. Min Act: -0.1700
Data Index: 431266 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4986. Min Range: -6.4986
Max Act: 6.0299. Min Act: -0.1700
Data Index: 3122451 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4986. Min Range: -6.4986
Max Act: 5.9674. Min Act: -0.1700
Data Index: 8396545 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4986. Min Range: -6.4986
Max Act: 5.9986. Min Act: -0.1700
Data Index: 5784820 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4986. Min Range: -6.4986
Max Act: 5.9674. Min Act: -0.1700
Data Index: 4953781 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4986. Min Range: -6.4986
Max Act: 5.9986. Min Act: -0.1700
Data Index: 2880299 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4986. Min Range: -6.4986
Max Act: 5.9674. Min Act: -0.1700
Data Index: 5311548 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4986. Min Range: -6.4986
Max Act: 5.9049. Min Act: -0.1700
Data Index: 2696056 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4986. Min Range: -6.4986
Max Act: 5.9361. Min Act: -0.1700
Data Index: 4607955 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19