Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3263 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.5519. Min Act: -0.1700
Data Index: 6882669 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.5519. Min Act: -0.1700
Data Index: 1139883 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.5206. Min Act: -0.1700
Data Index: 2522714 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.5206. Min Act: -0.1700
Data Index: 428325 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.5206. Min Act: -0.1700
Data Index: 3200773 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.5206. Min Act: -0.1700
Data Index: 2354174 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.5206. Min Act: -0.1700
Data Index: 11223 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.4892. Min Act: -0.1700
Data Index: 8718909 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.4579. Min Act: -0.1700
Data Index: 6036459 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.4579. Min Act: -0.1700
Data Index: 3361654 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.4579. Min Act: -0.1700
Data Index: 122342 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.4579. Min Act: -0.1700
Data Index: 8764138 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.4266. Min Act: -0.1700
Data Index: 1569658 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.4266. Min Act: -0.1700
Data Index: 5452341 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.4266. Min Act: -0.1700
Data Index: 6142398 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.4266. Min Act: -0.1700
Data Index: 5792442 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.4266. Min Act: -0.1700
Data Index: 1596099 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.3952. Min Act: -0.1700
Data Index: 4958847 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.3952. Min Act: -0.1700
Data Index: 2257030 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5519. Min Range: -3.5519
Max Act: 3.3952. Min Act: -0.1700
Data Index: 4810233 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19