Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2587 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2739. Min Range: -8.2739
Max Act: 8.2739. Min Act: -0.1700
Data Index: 4998850 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2739. Min Range: -8.2739
Max Act: 8.2114. Min Act: -0.1700
Data Index: 6757554 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2739. Min Range: -8.2739
Max Act: 8.0551. Min Act: -0.1700
Data Index: 3841695 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.9614. Min Act: -0.1700
Data Index: 6337290 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.8989. Min Act: -0.1700
Data Index: 8348466 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.8364. Min Act: -0.1700
Data Index: 4010635 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.7739. Min Act: -0.1700
Data Index: 7093076 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.7426. Min Act: -0.1700
Data Index: 7448347 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.5864. Min Act: -0.1700
Data Index: 6629035 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.4926. Min Act: -0.1700
Data Index: 2576045 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.5239. Min Act: -0.1700
Data Index: 6877704 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.5239. Min Act: -0.1700
Data Index: 5667247 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.4301. Min Act: -0.1700
Data Index: 7007952 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.4301. Min Act: -0.1700
Data Index: 1824679 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.3989. Min Act: -0.1700
Data Index: 7262928 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.3676. Min Act: -0.1700
Data Index: 5818758 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.3676. Min Act: -0.1700
Data Index: 5629447 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.3676. Min Act: -0.1700
Data Index: 1503672 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.3676. Min Act: -0.1700
Data Index: 5099426 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2739. Min Range: -8.2739
Max Act: 7.3364. Min Act: -0.1700
Data Index: 341102 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19