Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.5029. Min Act: -0.1700
Data Index: 7284769 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.4379. Min Act: -0.1698
Data Index: 6006500 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.4053. Min Act: -0.1694
Data Index: 4605104 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.3890. Min Act: -0.1699
Data Index: 3630789 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.3563. Min Act: -0.1700
Data Index: 6421632 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.3399. Min Act: -0.1700
Data Index: 2344198 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.3235. Min Act: -0.1700
Data Index: 1581739 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.2741. Min Act: -0.1700
Data Index: 1465052 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.2741. Min Act: -0.1687
Data Index: 7153358 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.2906. Min Act: -0.1700
Data Index: 785958 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.2741. Min Act: -0.1700
Data Index: 8174786 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.2576. Min Act: -0.1700
Data Index: 5403985 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.2576. Min Act: -0.1700
Data Index: 3193362 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.2080. Min Act: -0.1642
Data Index: 3830259 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.2411. Min Act: -0.1698
Data Index: 2168723 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.2246. Min Act: -0.1597
Data Index: 8341054 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.2411. Min Act: -0.1699
Data Index: 8806423 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.2246. Min Act: -0.1693
Data Index: 4095756 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.2080. Min Act: -0.1699
Data Index: 218230 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5029. Min Range: -2.5029
Max Act: 2.1914. Min Act: -0.1699
Data Index: 6006501 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19