Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2138 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0255. Min Range: -6.0255
Max Act: 6.0255. Min Act: -0.1700
Data Index: 4621134 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.9005. Min Act: -0.1700
Data Index: 4076325 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.8692. Min Act: -0.1700
Data Index: 7980250 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.8067. Min Act: -0.1700
Data Index: 4504912 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.7130. Min Act: -0.1700
Data Index: 4174609 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.6817. Min Act: -0.1700
Data Index: 6905398 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.6817. Min Act: -0.1700
Data Index: 8526026 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.6817. Min Act: -0.1700
Data Index: 5721761 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.6817. Min Act: -0.1700
Data Index: 8732837 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.6817. Min Act: -0.1700
Data Index: 5217673 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.6505. Min Act: -0.1700
Data Index: 6217722 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.5880. Min Act: -0.1700
Data Index: 4028840 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.5567. Min Act: -0.1700
Data Index: 560583 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.5255. Min Act: -0.1700
Data Index: 694431 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.5255. Min Act: -0.1700
Data Index: 6936765 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.5255. Min Act: -0.1700
Data Index: 3432706 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.4942. Min Act: -0.1700
Data Index: 804551 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.4942. Min Act: -0.1700
Data Index: 6102196 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.4630. Min Act: -0.1700
Data Index: 8087525 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0255. Min Range: -6.0255
Max Act: 5.4630. Min Act: -0.1700
Data Index: 1501677 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19