Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3167 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5982. Min Range: -9.5982
Max Act: 9.5982. Min Act: -0.1700
Data Index: 8561685 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5982. Min Range: -9.5982
Max Act: 9.5982. Min Act: -0.1700
Data Index: 4098718 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5982. Min Range: -9.5982
Max Act: 9.3482. Min Act: -0.1700
Data Index: 4240317 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5982. Min Range: -9.5982
Max Act: 9.1607. Min Act: -0.1700
Data Index: 3252108 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5982. Min Range: -9.5982
Max Act: 9.1607. Min Act: -0.1700
Data Index: 595085 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5982. Min Range: -9.5982
Max Act: 9.1607. Min Act: -0.1700
Data Index: 8588850 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5982. Min Range: -9.5982
Max Act: 9.0982. Min Act: -0.1700
Data Index: 5932292 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5982. Min Range: -9.5982
Max Act: 9.0357. Min Act: -0.1700
Data Index: 8176150 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5982. Min Range: -9.5982
Max Act: 8.9732. Min Act: -0.1700
Data Index: 5570852 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5982. Min Range: -9.5982
Max Act: 8.9107. Min Act: -0.1700
Data Index: 8011586 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5982. Min Range: -9.5982
Max Act: 8.8482. Min Act: -0.1700
Data Index: 1281085 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5982. Min Range: -9.5982
Max Act: 8.8482. Min Act: -0.1700
Data Index: 6982248 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5982. Min Range: -9.5982
Max Act: 8.8482. Min Act: -0.1700
Data Index: 661306 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5982. Min Range: -9.5982
Max Act: 8.8482. Min Act: -0.1700
Data Index: 5795543 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5982. Min Range: -9.5982
Max Act: 8.8482. Min Act: -0.1700
Data Index: 4130239 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5982. Min Range: -9.5982
Max Act: 8.7857. Min Act: -0.1700
Data Index: 3882510 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5982. Min Range: -9.5982
Max Act: 8.7232. Min Act: -0.1700
Data Index: 5764865 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5982. Min Range: -9.5982
Max Act: 8.7232. Min Act: -0.1700
Data Index: 2496773 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5982. Min Range: -9.5982
Max Act: 8.7232. Min Act: -0.1700
Data Index: 433374 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5982. Min Range: -9.5982
Max Act: 8.7232. Min Act: -0.1700
Data Index: 529407 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19