Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1840 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.6621. Min Act: -0.1700
Data Index: 4788275 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.5996. Min Act: -0.1700
Data Index: 6618765 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.5371. Min Act: -0.1700
Data Index: 7344763 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.5371. Min Act: -0.1700
Data Index: 7493249 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.4746. Min Act: -0.1700
Data Index: 3803868 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.5371. Min Act: -0.1700
Data Index: 2074403 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.3496. Min Act: -0.1700
Data Index: 7743685 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.3496. Min Act: -0.1700
Data Index: 3644721 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.3496. Min Act: -0.1700
Data Index: 7297660 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.3496. Min Act: -0.1700
Data Index: 4144960 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.2871. Min Act: -0.1700
Data Index: 3820719 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.2871. Min Act: -0.1700
Data Index: 3469471 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.2871. Min Act: -0.1700
Data Index: 4875644 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.2246. Min Act: -0.1700
Data Index: 8388330 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.2246. Min Act: -0.1700
Data Index: 4335183 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.1621. Min Act: -0.1700
Data Index: 3318168 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.0996. Min Act: -0.1700
Data Index: 6876917 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.1621. Min Act: -0.1700
Data Index: 2734254 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.0996. Min Act: -0.1700
Data Index: 413466 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6621. Min Range: -8.6621
Max Act: 8.0996. Min Act: -0.1700
Data Index: 1946913 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19