Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 958 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4118. Min Range: -6.4118
Max Act: 6.4118. Min Act: -0.1700
Data Index: 7021872 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4118. Min Range: -6.4118
Max Act: 6.1305. Min Act: -0.1700
Data Index: 1857040 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4118. Min Range: -6.4118
Max Act: 6.0993. Min Act: -0.1700
Data Index: 4201243 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4118. Min Range: -6.4118
Max Act: 6.1305. Min Act: -0.1700
Data Index: 2816198 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4118. Min Range: -6.4118
Max Act: 6.0368. Min Act: -0.1700
Data Index: 3135948 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4118. Min Range: -6.4118
Max Act: 6.0368. Min Act: -0.1700
Data Index: 189647 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4118. Min Range: -6.4118
Max Act: 6.0368. Min Act: -0.1700
Data Index: 8401 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4118. Min Range: -6.4118
Max Act: 6.0055. Min Act: -0.1700
Data Index: 66560 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4118. Min Range: -6.4118
Max Act: 6.0055. Min Act: -0.1700
Data Index: 7368185 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4118. Min Range: -6.4118
Max Act: 6.0055. Min Act: -0.1700
Data Index: 7359906 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4118. Min Range: -6.4118
Max Act: 5.9743. Min Act: -0.1700
Data Index: 6544925 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4118. Min Range: -6.4118
Max Act: 5.9743. Min Act: -0.1700
Data Index: 8358079 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4118. Min Range: -6.4118
Max Act: 5.9743. Min Act: -0.1700
Data Index: 6879485 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4118. Min Range: -6.4118
Max Act: 5.9743. Min Act: -0.1700
Data Index: 6427173 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4118. Min Range: -6.4118
Max Act: 5.9118. Min Act: -0.1700
Data Index: 3211404 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4118. Min Range: -6.4118
Max Act: 5.8493. Min Act: -0.1700
Data Index: 6759425 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4118. Min Range: -6.4118
Max Act: 5.8493. Min Act: -0.1700
Data Index: 4238233 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4118. Min Range: -6.4118
Max Act: 5.8493. Min Act: -0.1700
Data Index: 3882874 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4118. Min Range: -6.4118
Max Act: 5.8493. Min Act: -0.1700
Data Index: 6087421 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4118. Min Range: -6.4118
Max Act: 5.8180. Min Act: -0.1700
Data Index: 1336105 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19