Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3824 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3518. Min Range: -5.3518
Max Act: 5.3206. Min Act: -0.1700
Data Index: 4894886 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3518. Min Range: -5.3518
Max Act: 5.3518. Min Act: -0.1700
Data Index: 3768280 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3518. Min Range: -5.3518
Max Act: 5.1956. Min Act: -0.1700
Data Index: 3283573 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3518. Min Range: -5.3518
Max Act: 5.1643. Min Act: -0.1700
Data Index: 5216777 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3518. Min Range: -5.3518
Max Act: 5.1018. Min Act: -0.1700
Data Index: 1492425 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3518. Min Range: -5.3518
Max Act: 5.0706. Min Act: -0.1700
Data Index: 1473001 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3518. Min Range: -5.3518
Max Act: 5.0706. Min Act: -0.1700
Data Index: 649051 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3518. Min Range: -5.3518
Max Act: 5.0393. Min Act: -0.1700
Data Index: 2426025 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3518. Min Range: -5.3518
Max Act: 4.9768. Min Act: -0.1700
Data Index: 2395435 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3518. Min Range: -5.3518
Max Act: 4.9768. Min Act: -0.1700
Data Index: 7258130 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3518. Min Range: -5.3518
Max Act: 4.9456. Min Act: -0.1700
Data Index: 4510284 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3518. Min Range: -5.3518
Max Act: 4.9456. Min Act: -0.1700
Data Index: 2106764 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3518. Min Range: -5.3518
Max Act: 4.9456. Min Act: -0.1700
Data Index: 6025899 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3518. Min Range: -5.3518
Max Act: 4.9456. Min Act: -0.1700
Data Index: 3582703 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3518. Min Range: -5.3518
Max Act: 4.9143. Min Act: -0.1700
Data Index: 3811003 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3518. Min Range: -5.3518
Max Act: 4.9143. Min Act: -0.1700
Data Index: 5138793 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3518. Min Range: -5.3518
Max Act: 4.9143. Min Act: -0.1700
Data Index: 433284 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3518. Min Range: -5.3518
Max Act: 4.9143. Min Act: -0.1700
Data Index: 1452742 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3518. Min Range: -5.3518
Max Act: 4.9143. Min Act: -0.1700
Data Index: 7942683 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3518. Min Range: -5.3518
Max Act: 4.9143. Min Act: -0.1700
Data Index: 4002551 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19