Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3489 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4906. Min Range: -6.4906
Max Act: 6.4906. Min Act: -0.1700
Data Index: 7869159 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4906. Min Range: -6.4906
Max Act: 6.2093. Min Act: -0.1700
Data Index: 5211198 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4906. Min Range: -6.4906
Max Act: 6.1781. Min Act: -0.1700
Data Index: 2603184 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4906. Min Range: -6.4906
Max Act: 6.1468. Min Act: -0.1700
Data Index: 4849573 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4906. Min Range: -6.4906
Max Act: 6.0218. Min Act: -0.1700
Data Index: 5648851 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.9593. Min Act: -0.1700
Data Index: 1465213 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.9593. Min Act: -0.1700
Data Index: 5113387 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.9281. Min Act: -0.1700
Data Index: 7183064 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.9281. Min Act: -0.1700
Data Index: 3688952 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.8968. Min Act: -0.1700
Data Index: 8218527 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.8656. Min Act: -0.1700
Data Index: 2413532 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.8656. Min Act: -0.1700
Data Index: 6324634 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.8656. Min Act: -0.1700
Data Index: 5453267 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.8031. Min Act: -0.1700
Data Index: 6268738 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.7718. Min Act: -0.1700
Data Index: 2016597 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.7718. Min Act: -0.1700
Data Index: 4605491 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.7718. Min Act: -0.1700
Data Index: 4730431 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.7718. Min Act: -0.1700
Data Index: 2770584 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.7406. Min Act: -0.1700
Data Index: 4049905 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4906. Min Range: -6.4906
Max Act: 5.7718. Min Act: -0.1700
Data Index: 5956602 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19