Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 492 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1500. Min Range: -3.1500
Max Act: 3.1500. Min Act: -0.1700
Data Index: 7822261 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1500. Min Range: -3.1500
Max Act: 3.0554. Min Act: -0.1700
Data Index: 3898385 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1500. Min Range: -3.1500
Max Act: 3.0870. Min Act: -0.1700
Data Index: 2535372 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1500. Min Range: -3.1500
Max Act: 3.0397. Min Act: -0.1700
Data Index: 7516618 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1500. Min Range: -3.1500
Max Act: 3.0239. Min Act: -0.1700
Data Index: 6829861 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1500. Min Range: -3.1500
Max Act: 3.0239. Min Act: -0.1700
Data Index: 8370634 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1500. Min Range: -3.1500
Max Act: 3.0239. Min Act: -0.1700
Data Index: 3810190 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1500. Min Range: -3.1500
Max Act: 3.0081. Min Act: -0.1700
Data Index: 2075989 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1500. Min Range: -3.1500
Max Act: 3.0081. Min Act: -0.1700
Data Index: 5005327 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1500. Min Range: -3.1500
Max Act: 3.0081. Min Act: -0.1700
Data Index: 2338750 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1500. Min Range: -3.1500
Max Act: 3.0081. Min Act: -0.1700
Data Index: 2669593 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1500. Min Range: -3.1500
Max Act: 2.9923. Min Act: -0.1700
Data Index: 3774139 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1500. Min Range: -3.1500
Max Act: 2.9923. Min Act: -0.1700
Data Index: 3710935 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1500. Min Range: -3.1500
Max Act: 2.9923. Min Act: -0.1700
Data Index: 2211026 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1500. Min Range: -3.1500
Max Act: 2.9923. Min Act: -0.1700
Data Index: 3650102 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1500. Min Range: -3.1500
Max Act: 2.9765. Min Act: -0.1700
Data Index: 5034391 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1500. Min Range: -3.1500
Max Act: 2.9606. Min Act: -0.1700
Data Index: 8272741 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1500. Min Range: -3.1500
Max Act: 2.9448. Min Act: -0.1700
Data Index: 1653333 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1500. Min Range: -3.1500
Max Act: 2.9448. Min Act: -0.1700
Data Index: 7750121 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1500. Min Range: -3.1500
Max Act: 2.9448. Min Act: -0.1700
Data Index: 3793880 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19