Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1054 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4896. Min Range: -12.4896
Max Act: 12.4896. Min Act: -0.1700
Data Index: 6548167 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4896. Min Range: -12.4896
Max Act: 12.1771. Min Act: -0.1700
Data Index: 1816219 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.9271. Min Act: -0.1700
Data Index: 2591353 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.8646. Min Act: -0.1700
Data Index: 3984009 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.8646. Min Act: -0.1700
Data Index: 6878069 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.8646. Min Act: -0.1700
Data Index: 6051786 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.8646. Min Act: -0.1700
Data Index: 7339895 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.8021. Min Act: -0.1700
Data Index: 6371866 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.6146. Min Act: -0.1700
Data Index: 4276039 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.6771. Min Act: -0.1700
Data Index: 6837211 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.5521. Min Act: -0.1700
Data Index: 3113292 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.6771. Min Act: -0.1700
Data Index: 857987 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.4896. Min Act: -0.1693
Data Index: 8450515 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.4896. Min Act: -0.1700
Data Index: 8179322 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.4271. Min Act: -0.1700
Data Index: 4298610 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.4271. Min Act: -0.1700
Data Index: 3888114 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.4271. Min Act: -0.1700
Data Index: 2026031 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.3646. Min Act: -0.1700
Data Index: 1080994 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.3646. Min Act: -0.1700
Data Index: 4214865 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4896. Min Range: -12.4896
Max Act: 11.3021. Min Act: -0.1700
Data Index: 6396271 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19