Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1321 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1283. Min Range: -6.1283
Max Act: 6.1283. Min Act: -0.1700
Data Index: 708084 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1283. Min Range: -6.1283
Max Act: 6.0658. Min Act: -0.1700
Data Index: 6641664 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1283. Min Range: -6.1283
Max Act: 6.0658. Min Act: -0.1700
Data Index: 7355760 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1283. Min Range: -6.1283
Max Act: 6.0033. Min Act: -0.1700
Data Index: 2029683 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.9721. Min Act: -0.1700
Data Index: 8816365 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.9408. Min Act: -0.1700
Data Index: 1786896 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.8783. Min Act: -0.1700
Data Index: 7023773 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.9096. Min Act: -0.1700
Data Index: 4556229 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.8471. Min Act: -0.1700
Data Index: 5747964 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.8471. Min Act: -0.1700
Data Index: 5574229 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.8471. Min Act: -0.1700
Data Index: 7163 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.8158. Min Act: -0.1700
Data Index: 2505231 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.7846. Min Act: -0.1700
Data Index: 8199471 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.7846. Min Act: -0.1700
Data Index: 5920653 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.7533. Min Act: -0.1700
Data Index: 6522373 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.7533. Min Act: -0.1700
Data Index: 5801350 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.7221. Min Act: -0.1700
Data Index: 5802430 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.6908. Min Act: -0.1700
Data Index: 2313002 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.6908. Min Act: -0.1700
Data Index: 2021948 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1283. Min Range: -6.1283
Max Act: 5.6596. Min Act: -0.1700
Data Index: 7949558 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19