Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1431 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2060. Min Range: -3.2060
Max Act: 3.2060. Min Act: -0.1700
Data Index: 3715888 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2060. Min Range: -3.2060
Max Act: 3.1430. Min Act: -0.1700
Data Index: 6056462 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2060. Min Range: -3.2060
Max Act: 3.1273. Min Act: -0.1700
Data Index: 5192171 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.9695. Min Act: -0.1700
Data Index: 284667 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.9695. Min Act: -0.1700
Data Index: 173803 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.9536. Min Act: -0.1700
Data Index: 463125 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.8585. Min Act: -0.1700
Data Index: 2151506 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.8903. Min Act: -0.1700
Data Index: 563725 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.8426. Min Act: -0.1700
Data Index: 7198447 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.8267. Min Act: -0.1700
Data Index: 8432151 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.8108. Min Act: -0.1700
Data Index: 8429355 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.8267. Min Act: -0.1700
Data Index: 8830164 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.7949. Min Act: -0.1700
Data Index: 6131113 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.8108. Min Act: -0.1700
Data Index: 8175687 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.8108. Min Act: -0.1700
Data Index: 6664966 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.7949. Min Act: -0.1700
Data Index: 8607071 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.7949. Min Act: -0.1700
Data Index: 6318867 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.7789. Min Act: -0.1700
Data Index: 6829575 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.7789. Min Act: -0.1700
Data Index: 2834141 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2060. Min Range: -3.2060
Max Act: 2.7949. Min Act: -0.1700
Data Index: 600102 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19