Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4206 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0624. Min Range: -8.0624
Max Act: 8.0624. Min Act: -0.1700
Data Index: 1971284 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.9686. Min Act: -0.1700
Data Index: 3940036 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.5311. Min Act: -0.1700
Data Index: 5785277 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.4999. Min Act: -0.1700
Data Index: 2842244 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.4999. Min Act: -0.1700
Data Index: 1019645 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.4374. Min Act: -0.1700
Data Index: 5655654 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.4061. Min Act: -0.1700
Data Index: 1554173 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.4061. Min Act: -0.1700
Data Index: 1580337 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.3749. Min Act: -0.1700
Data Index: 7798088 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.3124. Min Act: -0.1700
Data Index: 8081426 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.2811. Min Act: -0.1700
Data Index: 1495498 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.2186. Min Act: -0.1700
Data Index: 3166838 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.1874. Min Act: -0.1700
Data Index: 1748026 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.1561. Min Act: -0.1700
Data Index: 6864282 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.2186. Min Act: -0.1700
Data Index: 6168841 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.1874. Min Act: -0.1700
Data Index: 2032821 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.1561. Min Act: -0.1700
Data Index: 1145743 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.1561. Min Act: -0.1700
Data Index: 3971866 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.1249. Min Act: -0.1700
Data Index: 2494346 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0624. Min Range: -8.0624
Max Act: 7.1249. Min Act: -0.1700
Data Index: 1314315 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19