Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0943. Min Range: -7.0943
Max Act: 7.0943. Min Act: -0.1700
Data Index: 5823221 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.9381. Min Act: -0.1700
Data Index: 6224162 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.9068. Min Act: -0.1700
Data Index: 3864207 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.9381. Min Act: -0.1700
Data Index: 5504340 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.9068. Min Act: -0.1700
Data Index: 2180681 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.8443. Min Act: -0.1700
Data Index: 5007011 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.8443. Min Act: -0.1700
Data Index: 1869871 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.7506. Min Act: -0.1700
Data Index: 8343107 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.7506. Min Act: -0.1700
Data Index: 4270657 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.7193. Min Act: -0.1700
Data Index: 8568559 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.7193. Min Act: -0.1700
Data Index: 845245 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.7193. Min Act: -0.1700
Data Index: 7995957 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.6881. Min Act: -0.1700
Data Index: 4519178 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.6881. Min Act: -0.1700
Data Index: 6167790 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.6568. Min Act: -0.1700
Data Index: 3238604 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.6256. Min Act: -0.1700
Data Index: 899475 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.6881. Min Act: -0.1700
Data Index: 7911484 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.6568. Min Act: -0.1700
Data Index: 3924237 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.6256. Min Act: -0.1700
Data Index: 6008868 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0943. Min Range: -7.0943
Max Act: 6.6256. Min Act: -0.1700
Data Index: 3785993 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19