Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5843 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.3500. Min Act: -0.1700
Data Index: 7737622 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1937. Min Act: -0.1700
Data Index: 8364003 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.9749. Min Act: -0.1700
Data Index: 825749 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.0062. Min Act: -0.1700
Data Index: 6389142 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.0062. Min Act: -0.1700
Data Index: 7506966 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.0062. Min Act: -0.1700
Data Index: 617735 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.9749. Min Act: -0.1700
Data Index: 8538478 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.9437. Min Act: -0.1700
Data Index: 2157329 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.9437. Min Act: -0.1700
Data Index: 8727994 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.9124. Min Act: -0.1700
Data Index: 8663334 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.9124. Min Act: -0.1700
Data Index: 2485749 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.8811. Min Act: -0.1700
Data Index: 5916829 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.8811. Min Act: -0.1700
Data Index: 1803216 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.8499. Min Act: -0.1700
Data Index: 1790779 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.8186. Min Act: -0.1700
Data Index: 6244668 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.8186. Min Act: -0.1700
Data Index: 194779 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.8342. Min Act: -0.1700
Data Index: 8012030 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.8186. Min Act: -0.1700
Data Index: 2136219 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.8029. Min Act: -0.1700
Data Index: 7512818 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3500. Min Range: -4.3500
Max Act: 3.7873. Min Act: -0.1700
Data Index: 5006582 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19