Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.2281. Min Act: -0.1700
Data Index: 4099254 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.1344. Min Act: -0.1700
Data Index: 3348664 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.0406. Min Act: -0.1700
Data Index: 4820772 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.9781. Min Act: -0.1700
Data Index: 8793293 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.9781. Min Act: -0.1700
Data Index: 7781304 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8844. Min Act: -0.1700
Data Index: 7990461 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8844. Min Act: -0.1700
Data Index: 163324 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8844. Min Act: -0.1700
Data Index: 3380530 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8844. Min Act: -0.1700
Data Index: 4683696 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8531. Min Act: -0.1700
Data Index: 4474476 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8219. Min Act: -0.1700
Data Index: 2688112 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8219. Min Act: -0.1700
Data Index: 5217236 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8219. Min Act: -0.1700
Data Index: 4401130 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8219. Min Act: -0.1700
Data Index: 6012643 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.7906. Min Act: -0.1700
Data Index: 2857504 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.7906. Min Act: -0.1700
Data Index: 7795619 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.7906. Min Act: -0.1700
Data Index: 584359 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.7906. Min Act: -0.1700
Data Index: 3378567 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.7594. Min Act: -0.1700
Data Index: 6469111 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.7906. Min Act: -0.1700
Data Index: 1063281 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19