Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1796 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2371. Min Act: -0.1700
Data Index: 3013566 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1746. Min Act: -0.1700
Data Index: 6786347 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1746. Min Act: -0.1700
Data Index: 6527375 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1434. Min Act: -0.1700
Data Index: 2607552 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1434. Min Act: -0.1700
Data Index: 192353 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1434. Min Act: -0.1700
Data Index: 6527373 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1434. Min Act: -0.1700
Data Index: 2177651 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1434. Min Act: -0.1700
Data Index: 3691782 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.0809. Min Act: -0.1700
Data Index: 3861541 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.0184. Min Act: -0.1700
Data Index: 645388 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9871. Min Act: -0.1700
Data Index: 888494 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9871. Min Act: -0.1700
Data Index: 1939420 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9559. Min Act: -0.1700
Data Index: 4165094 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8934. Min Act: -0.1700
Data Index: 4783649 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8934. Min Act: -0.1700
Data Index: 463213 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9246. Min Act: -0.1700
Data Index: 1260426 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8934. Min Act: -0.1700
Data Index: 1417496 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8934. Min Act: -0.1700
Data Index: 4064776 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8934. Min Act: -0.1700
Data Index: 888500 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8934. Min Act: -0.1700
Data Index: 361613 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19