Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3311 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2085. Min Range: -7.2085
Max Act: 7.2085. Min Act: -0.1700
Data Index: 1282969 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2085. Min Range: -7.2085
Max Act: 7.0835. Min Act: -0.1700
Data Index: 843795 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2085. Min Range: -7.2085
Max Act: 7.0523. Min Act: -0.1700
Data Index: 7205003 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.9273. Min Act: -0.1700
Data Index: 4596677 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.8960. Min Act: -0.1700
Data Index: 8352567 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.8335. Min Act: -0.1700
Data Index: 5203546 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.7710. Min Act: -0.1700
Data Index: 7399344 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.7398. Min Act: -0.1700
Data Index: 3036290 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.7398. Min Act: -0.1700
Data Index: 5197846 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.6773. Min Act: -0.1700
Data Index: 8117879 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.7085. Min Act: -0.1700
Data Index: 84095 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.6460. Min Act: -0.1700
Data Index: 4687173 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.5835. Min Act: -0.1700
Data Index: 4625905 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.5523. Min Act: -0.1700
Data Index: 7067277 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.5523. Min Act: -0.1700
Data Index: 5992103 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.5210. Min Act: -0.1700
Data Index: 5557819 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.4898. Min Act: -0.1700
Data Index: 1750358 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.4898. Min Act: -0.1700
Data Index: 3140341 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.4585. Min Act: -0.1700
Data Index: 7812909 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2085. Min Range: -7.2085
Max Act: 6.4585. Min Act: -0.1700
Data Index: 4480892 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19